INDEX

Explanations

the word "Bron" with varying levels of intensity

oai_token-act-pair · gpt-3.5-turbo

occurrences of the name "Bron" within the text

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

URA

-0.74

EPA

-0.65

RESULTS

-0.63

yrinth

-0.62

ACTION

-0.62

 Biological

-0.62

Spy

-0.62

EMP

-0.60

stress

-0.59

 Archives

-0.59

POSITIVE LOGITS

fman

1.27

zes

1.09

wyn

1.05

zos

0.99

hma

0.96

etooth

0.94

neys

0.91

wen

0.91

osure

0.90

hm

0.89

Activations Density 0.018%

the word "Bron" with varying levels of intensity

occurrences of the name "Bron" within the text

No Comments

No Known Activations