INDEX

Explanations

prominent thematic indicators or transitions in the text

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

determiners and prepositions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.20.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

oredCriteria

-0.40

sendLogPayload

-0.38

remel

-0.37

Derbyniad

-0.37

וויק

-0.36

 pinulongan

-0.36

 vacuum

-0.36

umbledore

-0.35

riezmann

-0.35

eapple

-0.35

POSITIVE LOGITS

 propOrder

0.65

 defaultstate

0.65

 <<<<<<<<<<<<<<

0.59

 صوتيه

0.58

 surla

0.58

transQ

0.54

UrlResolution

0.51

 GenerationType

0.50

 CreateTagHelper

0.50

MigrationBuilder

0.48

Activations Density 0.412%

prominent thematic indicators or transitions in the text

determiners and prepositions

No Comments

No Known Activations