INDEX

Explanations

the word "uh" repeated several times with varying levels of activation

oai_token-act-pair · gpt-3.5-turbo

expressions of disbelief or surprise

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

BOOK

-0.73

 Reborn

-0.73

BALL

-0.70

 Painter

-0.68

uncture

-0.67

ersen

-0.67

chnology

-0.66

å¥³

-0.65

ãĥ¼ãĥĨãĤ£

-0.62

ertodd

-0.61

POSITIVE LOGITS

ahah

1.15

awk

1.03

ansen

0.96

awks

0.95

ospital

0.95

undai

0.92

hhhh

0.90

annah

0.87

arsh

0.83

hh

0.82

Activations Density 0.015%

the word "uh" repeated several times with varying levels of activation

expressions of disbelief or surprise

No Comments

No Known Activations