INDEX

Explanations

phrases related to specific events or incidents

oai_token-act-pair · gpt-3.5-turbo

references to specific events or incidents

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

SPONSORED

-0.85

 another

-0.71

 coincides

-0.68

 differs

-0.66

ency

-0.65

 accompl

-0.64

else

-0.63

 aside

-0.63

 whichever

-0.63

 besides

-0.62

POSITIVE LOGITS

 ones

1.47

 aforementioned

1.13

 infamous

0.86

 Ones

0.76

 dreaded

0.71

unts

0.69

 likes

0.68

 Dalai

0.68

 famous

0.68

 obligatory

0.68

Activations Density 0.224%

phrases related to specific events or incidents

references to specific events or incidents

No Comments

No Known Activations