INDEX

Explanations

single-letter 'C' followed by the number '9' or '10'

oai_token-act-pair · gpt-3.5-turbo

specific characters or symbols

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

 Yamaha

-0.64

 Tinder

-0.64

 timeout

-0.64

 life

-0.60

 Lange

-0.60

Sov

-0.60

 Gors

-0.60

 advers

-0.60

 baskets

-0.59

 bottleneck

-0.58

POSITIVE LOGITS

URRENT

1.31

overed

1.29

ategories

1.27

onsequ

1.26

rouch

1.20

ursed

1.18

ategor

1.18

riminal

1.17

onduct

1.17

ologne

1.17

Activations Density 0.062%

single-letter 'C' followed by the number '9' or '10'

specific characters or symbols

No Comments

No Known Activations