INDEX

Explanations

geographical references and descriptions of locations

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

capes and points of land

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

Negative Logits

 Bradford

-0.44

ypal

-0.41

Psych

-0.40

 payroll

-0.40

Arcade

-0.40

 Kano

-0.39

 induc

-0.39

 betweenstory

-0.39

forum

-0.39

 inves

-0.39

POSITIVE LOGITS

tip

0.75

extrémité

0.75

 punta

0.74

 Cape

0.69

 extremity

0.68

 Point

0.68

 promont

0.66

 cape

0.66

tip

0.65

Cape

0.65

Activations Density 0.036%

geographical references and descriptions of locations

capes and points of land

No Known Activations