INDEX

Explanations

specific names of political figures

oai_token-act-pair · gpt-3.5-turbo

names of political figures associated with a resignation or controversy

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

 Minotaur

-0.80

 Jericho

-0.73

omas

-0.73

 Viking

-0.71

otropic

-0.69

olithic

-0.69

 Gemini

-0.66

istically

-0.65

odus

-0.63

orate

-0.62

POSITIVE LOGITS

 Wasserman

1.16

 Schultz

1.05

ignt

0.84

wcs

0.77

engers

0.71

etti

0.71

 Tanz

0.71

Leaks

0.71

staff

0.70

urations

0.69

Activations Density 0.017%

specific names of political figures

names of political figures associated with a resignation or controversy

No Comments

No Known Activations