INDEX

Explanations

proper nouns

oai_token-act-pair · gpt-3.5-turbo

the end of text markers or similar delimiters indicating separate entries or descriptions

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

[&

-0.70

 ..."

-0.70

 Thumbnails

-0.66

ãĥīãĥ©ãĤ´ãĥ³

-0.64

åĤ

-0.62

 guiActiveUnfocused

-0.60

 civilian

-0.60

 à¨

-0.58

 âĢ¦"

-0.57

ãĥīãĥ©

-0.56

POSITIVE LOGITS

jamin

1.00

odore

1.00

dinand

0.96

arnaev

0.93

ogether

0.92

withstanding

0.85

ucci

0.85

resa

0.84

utsche

0.84

nesty

0.82

Activations Density 0.229%

proper nouns

the end of text markers or similar delimiters indicating separate entries or descriptions

No Comments

No Known Activations