INDEX

Explanations

mentions of political figures and positions

oai_token-act-pair · gpt-3.5-turbo

the word "shadow" and its contextual uses

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

urses

-0.91

awaru

-0.77

renheit

-0.76

anchester

-0.75

apsed

-0.74

unker

-0.73

tics

-0.73

keye

-0.71

OPLE

-0.71

Attempts

-0.70

POSITIVE LOGITS

moon

0.98

 shadow

0.94

 Shadow

0.93

shadow

0.87

loo

0.83

Shadow

0.80

 Shadows

0.75

boxing

0.75

dust

0.75

busters

0.75

Activations Density 0.015%

mentions of political figures and positions

the word "shadow" and its contextual uses

No Comments

No Known Activations