INDEX

Explanations

phrases indicating a contradiction or opposing viewpoint

oai_token-act-pair · gpt-3.5-turbo

affirmations or confirmations of statements

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

dayName

-0.95

 exting

-0.86

SourceFile

-0.82

bas

-0.81

 pione

-0.76

stal

-0.74

ãĤ¼ãĤ¦ãĤ¹

-0.73

 teasp

-0.72

ERT

-0.71

raq

-0.69

POSITIVE LOGITS

 some

1.05

 there

0.99

 sometimes

0.97

 SOME

0.95

 occasional

0.89

 mistakes

0.89

 occasionally

0.83

some

0.81

 disagreements

0.81

we

0.81

Activations Density 0.274%

phrases indicating a contradiction or opposing viewpoint

affirmations or confirmations of statements

No Comments

No Known Activations