INDEX

Explanations

proper nouns related to individuals involved in discussions or statements

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

 typelib

-0.61

OrBuilder

-0.57

awtextra

-0.55

ThroughAttribute

-0.55

Derbyniad

-0.54

็จ

-0.53

vier

-0.51

 Catawiki

-0.51

sû

-0.51

 словам

-0.50

POSITIVE LOGITS

AutoresizingMask

0.57

 Vikipedi

0.56

 ivelany

0.56

.*")]

0.54

 оригіналу

0.52

ManyToMany

0.52

 consultato

0.51

glTexCoord

0.50

Hentet

0.50

aguya

0.49

Activations Density 0.019%

proper nouns related to individuals involved in discussions or statements

No Comments

No Known Activations