INDEX

Explanations

references to European entities or locations

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

protobuf schema definitions

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

 Cumming

-0.41

 Wort

-0.36

mit

-0.36

 تض

-0.35

sz

-0.35

 Crowe

-0.35

 ло

-0.34

Ro

-0.34

slot

-0.34

miento

-0.34

POSITIVE LOGITS

ecore

2.33

OGND

0.74

AndEndTag

0.65

 tartalomajánló

0.62

 незавершена

0.62

 ujednoznacz

0.60

 endblock

0.60

dafx

0.59

 EconPapers

0.57

 AssemblyCulture

0.57

Activations Density 0.001%

references to European entities or locations

protobuf schema definitions

No Comments

No Known Activations