INDEX

Explanations

phrases that indicate insincerity or superficiality in communication

oai_token-act-pair · gpt-4o-mini

New Auto-Interp

Configuration

chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.12.hook_resid_post

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

32,768

Data Type

float32

Hook Name

blocks.12.hook_resid_post

Architecture

jumprelu

Context Size

1,024

Dataset

chanind/pile-uncopyrighted-gemma-1024-abbrv-1B

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

UnusedPrivate

-0.69

 neri

-0.66

marle

-0.64

DoubleQuotes

-0.63

ScopeManager

-0.63

Efq

-0.62

 bewust

-0.62

ագրություններ

-0.60

 curio

-0.60

DebuggerStep

-0.59

POSITIVE LOGITS

ioutil

0.61

DockStyle

0.55

but

0.47

MultipartFile

0.42

Promises

0.42

 promise

0.42

 promises

0.42

requireNonNull

0.41

 mutta

0.40

labelledby

0.40

Activations Density 0.123%

phrases that indicate insincerity or superficiality in communication

No Comments

No Known Activations