INDEX

Explanations

verbs related to physical actions and objects that can be manipulated, often in a forceful or abrupt manner

oai_token-act-pair · gpt-3.5-turbo

terms and phrases related to visual experiences or observations

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

æĢ

-0.85

¿½

-0.83

©¶æ¥µ

-0.77

SEA

-0.76

TEXTURE

-0.73

£ı

-0.72

èª

-0.71

ãĥ¯ãĥ³

-0.71

OHN

-0.70

Reloaded

-0.68

POSITIVE LOGITS

itaire

0.85

 extraord

0.83

 soup

0.76

hers

0.75

coon

0.74

worm

0.71

 contam

0.69

 mids

0.68

inis

0.67

iasis

0.67

Activations Density 0.677%

verbs related to physical actions and objects that can be manipulated, often in a forceful or abrupt manner

terms and phrases related to visual experiences or observations

No Comments

No Known Activations