INDEX

Explanations

companies or brands

oai_token-act-pair · gpt-3.5-turbo

instances of the word "Win" in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

 gravity

-0.70

 populated

-0.65

£ı

-0.65

gat

-0.61

 intestine

-0.61

 pree

-0.60

 reservations

-0.59

 warr

-0.59

 reluct

-0.59

 moon

-0.59

POSITIVE LOGITS

ners

1.26

throp

1.17

frey

1.13

ning

1.08

ston

1.06

fred

1.02

nings

1.02

emaker

0.99

ters

0.97

kel

0.97

Activations Density 0.023%

companies or brands

instances of the word "Win" in various contexts

No Comments

No Known Activations