INDEX

Explanations

mentions of specific herbs and ingredients used in cooking

oai_token-act-pair · gpt-3.5-turbo

mentions of specific herbs and names

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

KEN

-0.80

lasses

-0.77

ceed

-0.75

ramer

-0.74

ffen

-0.74

RAY

-0.72

bered

-0.72

vP

-0.72

lass

-0.71

bler

-0.71

POSITIVE LOGITS

icas

0.84

alam

0.78

icate

0.78

hyde

0.78

itect

0.78

icum

0.77

utical

0.70

 sidewalks

0.69

 metic

0.67

yard

0.66

Activations Density 0.044%

mentions of specific herbs and ingredients used in cooking

mentions of specific herbs and names

No Comments

No Known Activations