INDEX

Explanations

statements of declarations or announcements

oai_token-act-pair · gpt-3.5-turbo

the word "declare" and its variations in various contexts

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

enhagen

-0.70

ograp

-0.70

alez

-0.69

 partName

-0.68

udes

-0.65

ographers

-0.64

CRIP

-0.64

ramid

-0.63

WARE

-0.62

tips

-0.62

POSITIVE LOGITS

 bankruptcy

1.10

war

1.03

 victory

1.03

 unequivocally

1.02

 allegiance

1.00

 independence

0.98

 martial

0.95

phas

0.93

 unconstitutional

0.87

 truce

0.84

Activations Density 0.061%

statements of declarations or announcements

the word "declare" and its variations in various contexts

No Comments

No Known Activations