INDEX

Explanations

mentions of specific political figures like President Obama

oai_token-act-pair · gpt-3.5-turbo

mentions of political figures, particularly Barack Obama and Donald Trump

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

MJ

-0.77

Offline

-0.72

NP

-0.66

 mats

-0.65

ãĤ¯

-0.64

 notebooks

-0.64

 dates

-0.64

Tokens

-0.64

 probabilities

-0.61

coins

-0.61

POSITIVE LOGITS

ÃŃs

0.88

 vetoed

0.80

 Presents

0.78

 Jinping

0.76

 assembled

0.75

 pard

0.72

iets

0.69

hower

0.68

enstein

0.68

 Appears

0.68

Activations Density 0.062%

mentions of specific political figures like President Obama

mentions of political figures, particularly Barack Obama and Donald Trump

No Comments

No Known Activations