INDEX

Explanations

chemical compounds and university names

oai_token-act-pair · gpt-3.5-turbo

chemical components and institutional names

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

Args

-0.55

orius

-0.52

rontal

-0.50

Wik

-0.48

destruct

-0.47

etsk

-0.47

olina

-0.46

Mods

-0.46

matic

-0.46

 condos

-0.46

POSITIVE LOGITS

phia

0.69

sels

0.59

owship

0.53

iston

0.51

lehem

0.50

estone

0.49

elson

0.49

atters

0.49

 Bever

0.48

estival

0.48

Activations Density 1.246%

chemical compounds and university names

chemical components and institutional names

No Comments

No Known Activations