INDEX

Explanations

phrases or sentences describing actions or states

oai_token-act-pair · gpt-3.5-turbo

instances of the verb "was" in various contexts

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

 Previous

-0.73

 Highlights

-0.72

inav

-0.70

Footnote

-0.69

 Purchase

-0.65

atives

-0.65

lev

-0.65

 Supports

-0.64

ESE

-0.63

 entails

-0.62

POSITIVE LOGITS

nt

1.09

wolves

1.03

 gonna

1.02

 supposed

0.96

wolf

0.95

hes

0.94

 definitely

0.93

 able

0.93

 going

0.89

 destined

0.87

Activations Density 0.449%

phrases or sentences describing actions or states

instances of the verb "was" in various contexts

No Comments

No Known Activations