INDEX

Explanations

phrases related to rankings or evaluations

oai_token-act-pair · gpt-3.5-turbo

references to sequels or continuations of series

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

 notor

-0.66

 redes

-0.65

 concess

-0.55

 comr

-0.55

 conduc

-0.55

 conflic

-0.55

ikuman

-0.54

oqu

-0.54

compl

-0.53

xual

-0.53

POSITIVE LOGITS

↵

0.90

 Anyway

0.89

;)

0.89

!!

0.88

<|endoftext|>

0.87

↵↵

0.86

↵Âł

0.86

!:

0.85

:)

0.84

!!!

0.83

Activations Density 1.238%

phrases related to rankings or evaluations

references to sequels or continuations of series

No Comments

No Known Activations