INDEX

Explanations

phrases related to hypothetical discussions and evaluations of actions or events

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

aarrggbb

-0.77

AsUp

-0.76

 незавершена

-0.76

ContentAsync

-0.69

 старости

-0.67

expandindo

-0.65

hoeddwyd

-0.65

цездатний

-0.63

FunctionFlags

-0.61

contentLoaded

-0.61

POSITIVE LOGITS

RenderAtEndOf

0.53

 Andrews

0.45

timation

0.44

estaw

0.43

tó

0.43

psack

0.43

ieste

0.43

cof

0.43

 grown

0.42

ásra

0.41

Activations Density 0.049%

phrases related to hypothetical discussions and evaluations of actions or events

No Comments

No Known Activations