INDEX

Explanations

elements that denote data structures or programming code

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

WebElementEntity

-0.75

 незавершена

-0.67

 AssemblyCulture

-0.67

 propOrder

-0.60

LookAnd

-0.56

 يتيمه

-0.55

 للمعارف

-0.54

wieś

-0.54

UrlResolution

-0.54

saraba

-0.54

POSITIVE LOGITS

toprule

0.39

TargetApi

0.38

 ostavi

0.36

 kebaya

0.33

큼

0.33

😐

0.33

 pretzels

0.32

 entran

0.32

 zure

0.32

Cuánto

0.32

Activations Density 0.000%

elements that denote data structures or programming code

<start_of_turn>user

No Comments

No Known Activations