INDEX

Explanations

words related to people's names, with a focus on the name "Claire"

oai_token-act-pair · gpt-3.5-turbo

the end of a document or a text segment

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

lar

-0.76

alling

-0.74

ksh

-0.74

balls

-0.72

MODE

-0.70

gra

-0.69

ALS

-0.69

tec

-0.69

BIP

-0.68

CVE

-0.68

POSITIVE LOGITS

ojure

0.97

avier

0.89

oner

0.82

osing

0.79

leans

0.78

othing

0.77

oning

0.76

inant

0.75

xus

0.74

osures

0.74

Activations Density 0.077%

words related to people's names, with a focus on the name "Claire"

the end of a document or a text segment

No Comments

No Known Activations