INDEX

Explanations

proper nouns related to political figures

oai_token-act-pair · gpt-3.5-turbo

instances of the term "Vice President."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

 exting

-0.64

 plate

-0.63

ANC

-0.61

 scenes

-0.60

banks

-0.60

 reservoirs

-0.59

 learners

-0.59

 birthplace

-0.58

 cruc

-0.57

glers

-0.57

POSITIVE LOGITS

iors

0.79

ially

0.72

 Clancy

0.71

ial

0.70

 Marshal

0.67

eur

0.67

Russ

0.66

stown

0.65

 Biden

0.65

OTUS

0.64

Activations Density 0.026%

proper nouns related to political figures

instances of the term "Vice President."

No Comments

No Known Activations