INDEX

Explanations

names of films or TV shows

oai_token-act-pair · gpt-3.5-turbo

words related to crime and legal issues

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

BO

-0.61

 Pace

-0.60

bound

-0.59

MP

-0.57

SM

-0.56

AW

-0.56

WR

-0.55

Arm

-0.54

 START

-0.54

 Factor

-0.53

POSITIVE LOGITS

theless

0.85

ciating

0.79

ilib

0.77

uration

0.77

sylvania

0.77

ukong

0.76

å§«

0.76

tenance

0.76

vous

0.75

ulty

0.73

Activations Density 0.161%

names of films or TV shows

words related to crime and legal issues

No Comments

No Known Activations