INDEX

Explanations

mentions of figurines or physical objects in a descriptive context

oai_token-act-pair · gpt-3.5-turbo

terms related to figures and their attributes in a broader context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

figure

-0.82

mitt

-0.79

mit

-0.71

 vain

-0.70

Fed

-0.66

fix

-0.63

hab

-0.63

clair

-0.61

figured

-0.61

vation

-0.61

POSITIVE LOGITS

inal

1.12

ians

1.06

ian

1.06

inations

1.04

inho

0.98

ine

0.95

anova

0.95

ines

0.93

inals

0.92

ative

0.91

Activations Density 0.086%

mentions of figurines or physical objects in a descriptive context

terms related to figures and their attributes in a broader context

No Comments

No Known Activations