INDEX

Explanations

duplicates or patterns of duplication in text

oai_token-act-pair · gpt-3.5-turbo

variations of the word "duplicate" and related concepts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

anwhile

-0.89

nee

-0.85

gamer

-0.84

liner

-0.77

morning

-0.73

ther

-0.72

tackle

-0.71

climate

-0.70

bell

-0.69

orsi

-0.68

POSITIVE LOGITS

 dupl

1.27

 duplication

1.24

 duplicate

1.20

icates

1.12

icative

1.02

 Dupl

0.94

 copies

0.92

icated

0.90

 negatives

0.89

 unfocusedRange

0.83

Activations Density 0.003%

duplicates or patterns of duplication in text

variations of the word "duplicate" and related concepts

No Comments

No Known Activations