INDEX

Explanations

terms related to citations and references within written text

oai_token-act-pair · gpt-3.5-turbo

sentence-ending punctuation marks

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

ient

-0.72

ettlement

-0.66

ierre

-0.64

olls

-0.64

ierra

-0.63

isons

-0.63

âķĲâķĲ

-0.63

ikuman

-0.62

 nearest

-0.61

ãĥ¼ãĥ³

-0.61

POSITIVE LOGITS

...]

1.36

âĢ¦]

1.21

Pg

1.01

note

0.98

?]

0.97

 citation

0.94

".[

0.90

Footnote

0.89

src

0.89

0.88

Activations Density 0.031%

terms related to citations and references within written text

sentence-ending punctuation marks

No Comments

No Known Activations