INDEX

Explanations

questions ending with question marks

oai_token-act-pair · gpt-3.5-turbo

questions that prompt introspection or inquiry about various topics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

athe

-0.71

ridor

-0.67

 encount

-0.66

itialized

-0.66

onds

-0.65

 ankles

-0.64

 glim

-0.63

aper

-0.63

aled

-0.62

eper

-0.62

POSITIVE LOGITS

 Surely

0.95

 Wouldn

0.93

 Nope

0.90

Why

0.90

.?

0.89

 Certainly

0.88

 Perhaps

0.86

 What

0.85

 Probably

0.85

 Would

0.84

Activations Density 0.090%

questions ending with question marks

questions that prompt introspection or inquiry about various topics

No Comments

No Known Activations