INDEX

Explanations

mentions of specific time periods or durations

oai_token-act-pair · gpt-3.5-turbo

numerical data or statistical figures

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

farious

-0.57

 destro

-0.56

æ©

-0.56

 helicop

-0.53

VL

-0.53

 Vaugh

-0.53

ueless

-0.52

ocrates

-0.50

abee

-0.50

emale

-0.49

POSITIVE LOGITS

 partName

0.57

 largeDownload

0.53

ARM

0.49

nces

0.45

\":

0.44

lur

0.44

 mourn

0.44

urches

0.42

vernment

0.41

MEM

0.41

Activations Density 0.996%

mentions of specific time periods or durations

numerical data or statistical figures

No Comments

No Known Activations