INDEX

Explanations

the word "Audi"

oai_token-act-pair · gpt-3.5-turbo

brand names related to the automotive and aerospace industries

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

yip

-0.81

tails

-0.81

ledge

-0.79

pter

-0.77

xual

-0.77

FUL

-0.74

arters

-0.73

fulness

-0.72

tty

-0.72

nown

-0.69

POSITIVE LOGITS

obook

1.18

ophile

1.07

oph

0.86

okin

0.85

omach

0.79

ometer

0.78

obile

0.78

atis

0.76

ograph

0.76

ographs

0.75

Activations Density 0.009%

the word "Audi"

brand names related to the automotive and aerospace industries

No Comments

No Known Activations