INDEX

Explanations

pronouns referring to individuals or groups

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

<start_of_turn> user

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

 AssemblyCompany

-0.59

BibitemShut

-0.57

 ModelExpression

-0.55

PerformLayout

-0.53

DataAnnotations

-0.50

⁬

-0.50

Према

-0.50

aires

-0.48

 Muriel

-0.48

Tops

-0.48

POSITIVE LOGITS

skjaer

0.39

 Roskov

0.36

 onCreateView

0.35

sbericht

0.35

IndentedString

0.35

 gabbana

0.32

Cyfeiriadau

0.30

 ivelany

0.30

 principle

0.29

quième

0.28

Activations Density 0.000%

pronouns referring to individuals or groups

<start_of_turn> user

No Comments

No Known Activations