INDEX

Explanations

references to related news or articles

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

ruary

-0.71

arer

-0.70

ãĤ©

-0.69

eg

-0.66

-0.65

ample

-0.65

ULT

-0.64

$$

-0.63

arest

-0.62

POSITIVE LOGITS

Related

1.01

 Cosponsors

0.85

 Related

0.82

 Factors

0.80

 Stories

0.77

 Occupations

0.77

eworthy

0.76

imedia

0.72

 condem

0.72

MORE

0.72

Activations Density 0.011%

related articles or news stories

references to related news or articles

No Comments

No Known Activations