INDEX

Explanations

phrases related to questioning reasons or explanations

oai_token-act-pair · gpt-3.5-turbo

inquiries related to reasons or explanations

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

olor

-0.66

 redeemed

-0.60

 redeem

-0.59

 occupancy

-0.58

 accur

-0.58

 equivalents

-0.57

 blending

-0.56

unn

-0.55

 taxp

-0.55

 rooft

-0.54

POSITIVE LOGITS

0.91

!?

0.86

?:

0.86

?!

0.74

so

0.73

 Hebdo

0.72

????

0.71

instead

0.71

?,

0.71

?????

0.71

Activations Density 0.369%

phrases related to questioning reasons or explanations

inquiries related to reasons or explanations

No Comments

No Known Activations