INDEX

Explanations

proper nouns related to political figures and events

oai_token-act-pair · gpt-3.5-turbo

instances of speeches made by prominent figures

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

EStreamFrame

-0.76

mol

-0.76

 fingert

-0.72

aea

-0.70

sci

-0.70

stice

-0.66

 eyeb

-0.66

pection

-0.65

 reuse

-0.65

pha

-0.65

POSITIVE LOGITS

 President

1.89

 Barack

1.77

 Hillary

1.57

 Obama

1.57

 Donald

1.55

President

1.54

 Trump

1.53

 Senator

1.50

 Secretary

1.47

 president

1.42

Activations Density 0.487%

proper nouns related to political figures and events

instances of speeches made by prominent figures

No Comments

No Known Activations