INDEX

Explanations

phrases indicating importance or necessity

oai_token-act-pair · gpt-3.5-turbo

the word "that" in various contexts throughout the text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

Nay

-0.65

 Centers

-0.64

 Pass

-0.64

IVERS

-0.62

 Directions

-0.59

 Occup

-0.58

ucc

-0.58

Gender

-0.58

throp

-0.57

mate

-0.57

POSITIVE LOGITS

soever

0.92

 fateful

0.86

 carbohyd

0.85

 pesky

0.83

 mattered

0.81

iago

0.78

 surrounds

0.78

ched

0.76

ÃĥÃĤ

0.75

eatures

0.75

Activations Density 0.443%

phrases indicating importance or necessity

the word "that" in various contexts throughout the text

No Comments

No Known Activations