INDEX

Explanations

official attributions or copyrights typically appearing at the end of articles

oai_token-act-pair · gpt-3.5-turbo

references to copyright or video content

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

hops

-0.90

cation

-0.79

 congr

-0.79

conom

-0.73

 cabinets

-0.68

IGF

-0.66

irlf

-0.66

ername

-0.65

swer

-0.65

Deg

-0.64

POSITIVE LOGITS

Jesus

0.71

Jer

0.69

ELL

0.68

Christian

0.66

 Alexandria

0.64

 Kurd

0.62

AMI

0.62

Las

0.62

 CHRIST

0.62

UCK

0.62

Activations Density 0.081%

official attributions or copyrights typically appearing at the end of articles

references to copyright or video content

No Comments

No Known Activations