INDEX

Explanations

phrases related to geographical locations

oai_token-act-pair · gpt-3.5-turbo

phrases indicating conditions or settings related to limitations or restrictions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

surprisingly

-0.53

hin

-0.52

 understatement

-0.51

answered

-0.51

hearted

-0.50

OUS

-0.50

ppa

-0.50

CRIPTION

-0.49

intention

-0.49

OSP

-0.48

POSITIVE LOGITS

 theirs

0.65

 otherwise

0.56

soever

0.51

arettes

0.51

 their

0.51

grades

0.50

 steroids

0.50

 engulf

0.49

edIn

0.49

ĨĴ

0.48

Activations Density 2.034%

phrases related to geographical locations

phrases indicating conditions or settings related to limitations or restrictions

No Comments

No Known Activations