INDEX

Explanations

instances where the word "data" appears

oai_token-act-pair · gpt-3.5-turbo

data and metrics related to various activities and their impacts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

icum

-0.76

otropic

-0.71

oshi

-0.68

ilic

-0.68

icol

-0.67

 chap

-0.64

obin

-0.61

icent

-0.60

elo

-0.59

oppy

-0.59

POSITIVE LOGITS

 FROM

1.43

 from

1.41

From

1.28

from

1.27

 From

1.21

)=(

0.85

Ø§ÙĦ

0.77

Reloaded

0.75

 originating

0.72

fro

0.72

Activations Density 0.139%

instances where the word "data" appears

data and metrics related to various activities and their impacts

No Comments

No Known Activations