INDEX

Explanations

expressions of approval or acceptance

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

-0.57

Useless

-0.56

 Virtu

-0.56

 Leal

-0.55

”،

-0.55

."));

-0.54

|','

-0.54

resu

-0.53

 "));

-0.53

PROMOTED

-0.52

POSITIVE LOGITS

 idéia

0.66

RTDA

0.65

imea

0.64

Clik

0.62

ineno

0.62

 okay

0.61

rungsseite

0.61

WebElementEntity

0.60

ParallelGroup

0.59

isOk

0.59

Activations Density 0.022%

expressions of approval or acceptance

No Comments

No Known Activations