INDEX

Explanations

phrases starting with "What's" or "What is."

oai_token-act-pair · gpt-3.5-turbo

the word "what."

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

 Lauder

-0.70

 resorts

-0.64

Ivy

-0.59

sie

-0.58

 segments

-0.57

 Zion

-0.57

 snail

-0.56

Hug

-0.55

 trusts

-0.53

 continents

-0.53

POSITIVE LOGITS

 happening

0.93

 gonna

0.93

omething

0.92

 transpired

0.87

 happened

0.85

wered

0.81

 happ

0.80

peed

0.79

ensibly

0.79

arthed

0.75

Activations Density 0.032%

phrases starting with "What's" or "What is."

the word "what."

No Comments

No Known Activations