INDEX

Explanations

informative words and phrases related to official communication or documentation

oai_token-act-pair · gpt-3.5-turbo

instances of communication or messages received

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

ãĥĦ

-0.68

usra

-0.66

ogi

-0.65

zai

-0.64

ERSON

-0.60

>>\

-0.60

Politics

-0.60

Bus

-0.59

guard

-0.59

ommod

-0.59

POSITIVE LOGITS

 these

1.38

 ones

1.36

 them

1.32

These

1.31

these

1.27

 These

1.18

 THESE

1.12

 THEM

1.05

 those

0.94

 originals

0.90

Activations Density 1.404%

informative words and phrases related to official communication or documentation

instances of communication or messages received

No Comments

No Known Activations