INDEX

Explanations

color descriptors related to food

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

colors followed by food

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.31.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

由

-0.43

ujud

-0.41

řel

-0.40

mıştır

-0.40

 experience

-0.39

 αξ

-0.39

omitempty

-0.38

complexContent

-0.38

Prod

-0.38

 satisfaction

-0.38

POSITIVE LOGITS

AndEndTag

0.57

 crunchy

0.44

extAlignment

0.44

 seasoning

0.44

ModelSerializer

0.43

 licor

0.43

 resourceCulture

0.42

 seasonings

0.42

 flaky

0.42

AutoScaleMode

0.41

Activations Density 0.012%

color descriptors related to food

colors followed by food

No Comments

No Known Activations