INDEX

Explanations

phrases related to exceeding boundaries or limits

oai_token-act-pair · gpt-3.5-turbo

variations of the word "step."

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

Negative Logits

binding

-0.66

gdala

-0.65

 Blueprint

-0.64

OUNT

-0.63

 eleph

-0.62

 Corpus

-0.62

 totality

-0.60

 Psycho

-0.60

Io

-0.60

inatory

-0.59

POSITIVE LOGITS

ste

1.25

chnology

1.01

lla

0.88

chn

0.86

Ste

0.84

pping

0.83

ering

0.82

arde

0.82

eling

0.81

alth

0.81

Activations Density 0.005%

phrases related to exceeding boundaries or limits

variations of the word "step."

No Known Activations