INDEX

Explanations

dates in the format "Month Year" and numbers written in ordinal form

oai_token-act-pair · gpt-3.5-turbo

specific dates and references to years

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

inki

-0.69

iland

-0.58

furt

-0.57

ãĥ¼ãĥĨ

-0.53

aline

-0.53

ĪĴ

-0.52

 redes

-0.51

urat

-0.50

uras

-0.49

TEXTURE

-0.48

POSITIVE LOGITS

hospital

0.58

scl

0.58

gov

0.49

ilts

0.46

daughter

0.46

ROR

0.46

 Jury

0.46

 Cyrus

0.46

oshenko

0.45

é¾į

0.44

Activations Density 1.642%

dates in the format "Month Year" and numbers written in ordinal form

specific dates and references to years

No Comments

No Known Activations