INDEX

Explanations

words related to definitions or explanations

oai_token-act-pair · gpt-3.5-turbo

phrases that define various concepts and terms

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

 outweigh

-0.83

umbn

-0.73

 heels

-0.72

BLIC

-0.72

aldi

-0.70

ibling

-0.69

ersen

-0.69

sync

-0.68

 applaud

-0.67

ÃĥÃĤ

-0.64

POSITIVE LOGITS

CoC

0.80

 boundaries

0.79

 thresholds

0.72

 defining

0.71

initions

0.71

Characters

0.70

 meaning

0.69

 definitions

0.68

 Species

0.68

Category

0.67

Activations Density 0.164%

words related to definitions or explanations

phrases that define various concepts and terms

No Comments

No Known Activations