INDEX

Explanations

phrases related to decisions or actions taken

oai_token-act-pair · gpt-3.5-turbo

the end of the document

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

Deal

-0.71

bub

-0.69

 Vaugh

-0.66

avorite

-0.66

[*

-0.65

bda

-0.65

cffff

-0.65

anu

-0.64

ADRA

-0.60

Recomm

-0.60

POSITIVE LOGITS

rogens

0.69

rogen

0.65

0.59

 therefore

0.59

 then

0.58

 Sons

0.58

 consequently

0.58

 thus

0.56

zbollah

0.54

rew

0.53

Activations Density 0.195%

phrases related to decisions or actions taken

the end of the document

No Comments

No Known Activations