INDEX

Explanations

names of individuals

oai_token-act-pair · gpt-3.5-turbo

mentions of specific individuals and entities, particularly names and proper nouns

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

venge

-0.75

changes

-0.70

 mortals

-0.70

externalActionCode

-0.69

displayText

-0.65

century

-0.64

 victimized

-0.64

©¶æ

-0.64

period

-0.64

 porous

-0.63

POSITIVE LOGITS

annon

1.29

ihilation

0.91

sburg

0.86

stadt

0.83

inational

0.81

igans

0.81

sonian

0.81

owitz

0.80

utterstock

0.80

ageddon

0.80

Activations Density 0.009%

names of individuals

mentions of specific individuals and entities, particularly names and proper nouns

No Comments

No Known Activations