INDEX

Explanations

phrases related to physical harm or injury

oai_token-act-pair · gpt-3.5-turbo

gerunds and participles in relation to actions or 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

Present

-0.79

lance

-0.73

present

-0.72

Îº

-0.68

draw

-0.68

ingen

-0.68

Jump

-0.66

writer

-0.66

staff

-0.66

lander

-0.65

POSITIVE LOGITS

imentary

0.85

axy

0.81

gorith

0.79

azar

0.78

gorithm

0.76

ergic

0.73

enaries

0.70

ISTER

0.70

arine

0.68

abama

0.68

Activations Density 0.016%

phrases related to physical harm or injury

gerunds and participles in relation to actions or activities

No Comments

No Known Activations