INDEX

Explanations

activities related to specific processes such as poaching, caching, hacking, mining, cooking, editing, styling, and harvesting

oai_token-act-pair · gpt-3.5-turbo

actions or processes that involve illegal or technical activities

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.hook_resid_pre

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.5.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

quart

-0.75

oubt

-0.65

âĢ²

-0.65

omet

-0.64

lihood

-0.64

xus

-0.63

ija

-0.62

nerg

-0.61

ika

-0.60

rogens

-0.60

POSITIVE LOGITS

HAM

0.94

 oneself

0.86

redients

0.81

 etiquette

0.74

 Grounds

0.73

 conventions

0.68

 purposes

0.66

 Practices

0.65

 Classes

0.65

 DRAG

0.65

Activations Density 0.263%

activities related to specific processes such as poaching, caching, hacking, mining, cooking, editing, styling, and harvesting

actions or processes that involve illegal or technical activities

No Comments

No Known Activations