INDEX

Explanations

complex phrases with detailed information or analysis

oai_token-act-pair · gpt-3.5-turbo

phrases indicating uncertainty or speculation

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

 simulator

-0.69

 mosqu

-0.62

 extraord

-0.57

à¦

-0.55

 accustomed

-0.53

erver

-0.52

utra

-0.52

 turret

-0.52

upd

-0.52

 traverse

-0.52

POSITIVE LOGITS

yet

0.68

mberg

0.66

acial

0.59

llah

0.58

>:

0.57

etheless

0.56

asures

0.55

 Scholars

0.54

_>

0.54

illance

0.54

Activations Density 1.428%

complex phrases with detailed information or analysis

phrases indicating uncertainty or speculation

No Comments

No Known Activations