INDEX

Explanations

the presence of the word "in" or its variations indicating context

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

MessageTagHelper

-0.72

 المعيارى

-0.63

AnchorStyles

-0.59

AnimationsModule

-0.58

 nonUne

-0.57

archiviato

-0.56

queryInterface

-0.56

UnusedPrivate

-0.55

MLLoader

-0.54

 Inscrivez

-0.54

POSITIVE LOGITS

 AssemblyTitle

0.42

complexContent

0.39

 oble

0.37

 internetowa

0.37

Acti

0.36

Cha

0.35

 Woolf

0.35

Weblinks

0.34

auf

0.34

导

0.34

Activations Density 0.000%

the presence of the word "in" or its variations indicating context

<start_of_turn> user

No Comments

No Known Activations