INDEX

Explanations

indicators of emotional or psychological states

oai_token-act-pair · gpt-4o-mini Triggered by @bot

Tokens preceding uncommon words

np_acts-logits-general · gemini-2.0-flash

body ;;;; ag

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

RetentionPolicy

-0.62

verwijspagina

-0.57

 ISNI

-0.57

 tartalomajánló

-0.57

higer

-0.57

ształ

-0.57

WebpackPlugin

-0.57

BoxShadow

-0.56

canestro

-0.54

 redor

-0.54

POSITIVE LOGITS

*/;

0.66

<blockquote>

0.61

*/

0.56

 Saltar

0.55

存于互联网档案馆

0.54

"]

0.53

Legături

0.53

*/;

0.53

pinMode

0.52

зия

0.52

Activations Density 0.080%

indicators of emotional or psychological states

Tokens preceding uncommon words

body ;;;; ag

No Comments

No Known Activations