INDEX

Explanations

French words, especially those related to organizations and locations

oai_token-act-pair · gpt-3.5-turbo

proper nouns and specific terms related to organizations and locations

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

KY

-0.77

MSN

-0.76

Ky

-0.74

urities

-0.70

tumblr

-0.69

staking

-0.69

schild

-0.69

Introduced

-0.68

terms

-0.67

visible

-0.66

POSITIVE LOGITS

itaire

0.92

 faire

0.61

 mathemat

0.60

 fatig

0.58

 Ninth

0.58

 Portug

0.58

 nephew

0.57

 Resort

0.56

 Latino

0.55

 facult

0.55

Activations Density 0.213%

French words, especially those related to organizations and locations

proper nouns and specific terms related to organizations and locations

No Comments

No Known Activations