INDEX

Explanations

names of places, people, and organizations

oai_token-act-pair · gpt-3.5-turbo

specific proper nouns and names related to various categories

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

enegger

-0.81

ãĥ¼ãĥĨ

-0.76

 destro

-0.71

terday

-0.71

ierrez

-0.66

anwhile

-0.63

oppable

-0.62

romeda

-0.62

 conclud

-0.61

gerald

-0.59

POSITIVE LOGITS

 Transfer

0.62

\":

0.58

 âĢº

0.57

izu

0.56

 Pixel

0.54

photos

0.53

 Shields

0.52

athi

0.52

 Deck

0.51

 Methods

0.51

Activations Density 0.419%

names of places, people, and organizations

specific proper nouns and names related to various categories

No Comments

No Known Activations