INDEX

Explanations

job listings and related terms

oai_token-act-pair · gpt-3.5-turbo

references to documents, reports, or announcements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 11-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.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

venge

-0.73

NULL

-0.68

âķĲ

-0.65

amping

-0.63

 Solitaire

-0.62

POSE

-0.59

 Decay

-0.59

atra

-0.58

ĵĺ

-0.58

ãĥĺ

-0.58

POSITIVE LOGITS

 reads

1.47

 indicates

1.43

 mentions

1.39

 describes

1.38

 says

1.37

 states

1.36

 suggests

1.29

 specifies

1.26

 depicts

1.26

 explains

1.25

Activations Density 0.314%

job listings and related terms

references to documents, reports, or announcements

No Comments

No Known Activations