INDEX

Explanations

phrases related to specific numbers or percentages

oai_token-act-pair · gpt-3.5-turbo

information related to statistical data and measurements

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

pta

-0.64

icum

-0.64

oppy

-0.60

ilic

-0.58

odox

-0.56

ently

-0.56

ãĥĩãĤ£

-0.54

WATCH

-0.54

errors

-0.53

icent

-0.53

POSITIVE LOGITS

 from

1.84

from

1.71

 FROM

1.63

From

1.50

 From

1.47

fro

0.85

 through

0.75

 originating

0.73

 derived

0.72

FR

0.71

Activations Density 0.194%

phrases related to specific numbers or percentages

information related to statistical data and measurements

No Comments

No Known Activations