INDEX

Explanations

words related to specific names or terms

oai_token-act-pair · gpt-3.5-turbo

words associated with horror or danger

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 11-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

isSpecial

-0.75

IST

-0.73

 sophistic

-0.73

 laun

-0.72

 advoc

-0.71

 incorpor

-0.70

 eleph

-0.68

 encount

-0.66

 Bent

-0.66

 administ

-0.65

POSITIVE LOGITS

1.56

ra

1.47

ras

1.45

rase

1.39

rah

1.38

rab

1.33

ron

1.26

ror

1.25

rain

1.25

rus

1.24

Activations Density 0.211%

words related to specific names or terms

words associated with horror or danger

No Comments

No Known Activations