INDEX

Explanations

mentions of positive phrases or affirmations

oai_token-act-pair · gpt-3.5-turbo

symbols or specific characters that do not belong to the standard alphabet

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

lees

-0.80

 bells

-0.78

assies

-0.77

 detectors

-0.74

 rooms

-0.73

 sights

-0.73

 levers

-0.73

 embassies

-0.73

 Vaugh

-0.71

 establishments

-0.71

POSITIVE LOGITS

fter

0.89

ccording

0.82

possibly

0.79

Cola

0.78

href

0.76

ighter

0.76

albeit

0.74

license

0.72

error

0.72

uthor

0.72

Activations Density 0.245%

mentions of positive phrases or affirmations

symbols or specific characters that do not belong to the standard alphabet

No Comments

No Known Activations