INDEX

Explanations

proper nouns related to political figures or entities

oai_token-act-pair · gpt-3.5-turbo

lists of endorsed individuals or items within a specific context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

olding

-0.78

uchi

-0.70

arden

-0.68

utters

-0.65

protection

-0.64

sense

-0.64

 confines

-0.64

old

-0.62

 Riyadh

-0.62

olds

-0.61

POSITIVE LOGITS

 notable

0.97

 noteworthy

0.96

 starred

0.92

 memorable

0.91

 featured

0.87

 ranked

0.85

 listed

0.85

 nominated

0.84

 participated

0.80

 endors

0.79

Activations Density 0.548%

proper nouns related to political figures or entities

lists of endorsed individuals or items within a specific context

No Comments

No Known Activations