INDEX

Explanations

phrases containing specific proper nouns and terms

oai_token-act-pair · gpt-3.5-turbo

specific terms or names related to locations and organizations

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Ô

-0.76

ĸļ

-0.71

enhagen

-0.67

chel

-0.67

interstitial

-0.61

INGTON

-0.61

theless

-0.60

Termin

-0.59

-0.58

inois

-0.57

POSITIVE LOGITS

 Corruption

0.84

sic

0.67

 Genius

0.67

 Equip

0.66

 Reconstruction

0.65

aceutical

0.63

 Lovely

0.61

 Subtle

0.60

alion

0.59

 Cruel

0.59

Activations Density 1.042%

phrases containing specific proper nouns and terms

specific terms or names related to locations and organizations

No Comments

No Known Activations