INDEX

Explanations

parentheses and square brackets used in written text

oai_token-act-pair · gpt-3.5-turbo

parentheses and brackets 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 @ 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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

cog

-0.87

 buoy

-0.83

Cth

-0.79

 redu

-0.76

 Puzz

-0.73

 wrink

-0.73

 creep

-0.71

 dense

-0.70

 embr

-0.70

 brim

-0.70

POSITIVE LOGITS

sic

1.85

laughs

1.44

emphasis

1.27

insert

1.25

the

1.24

exec

1.20

ex

1.17

police

1.17

his

1.16

another

1.15

Activations Density 0.060%

parentheses and square brackets used in written text

parentheses and brackets within the text

No Comments

No Known Activations