INDEX

Explanations

keywords related to interaction with others

oai_token-act-pair · gpt-3.5-turbo

references to other individuals or groups in the context of interactions and behaviors

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

Accessory

-0.72

itation

-0.71

ihara

-0.65

owship

-0.61

obar

-0.60

ocracy

-0.60

 Hulk

-0.60

oho

-0.59

 Warlock

-0.59

 centerpiece

-0.59

POSITIVE LOGITS

cius

0.88

ĸļ

0.83

ystem

0.79

ngth

0.79

 describ

0.78

 indo

0.76

paces

0.75

miah

0.75

 behavi

0.74

cript

0.73

Activations Density 0.032%

keywords related to interaction with others

references to other individuals or groups in the context of interactions and behaviors

No Comments

No Known Activations