INDEX

Explanations

Words related to specific actions or processes involving physical movement or manipulation

oai_token-act-pair · gpt-3.5-turbo

conjunctions and transitional phrases that indicate relationships among ideas

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

iciary

-0.71

ortium

-0.69

 sponsor

-0.68

 Lerner

-0.67

 issuer

-0.66

 publisher

-0.65

 Sloan

-0.64

arlane

-0.63

 Thomson

-0.63

 slate

-0.62

POSITIVE LOGITS

Downloadha

0.75

tons

0.74

rams

0.72

Integ

0.72

 stunts

0.71

Quotes

0.71

pause

0.70

Pattern

0.69

argon

0.68

nee

0.67

Activations Density 0.668%

Words related to specific actions or processes involving physical movement or manipulation

conjunctions and transitional phrases that indicate relationships among ideas

No Comments

No Known Activations