INDEX

Explanations

instances of uncertainty or inquiry about experiences or situations

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

common preceding words

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

AutoScale

-0.48

 iprot

-0.46

ChildScrollView

-0.45

 Paglinawan

-0.44

DockStyle

-0.44

<_>

-0.44

FormTagHelper

-0.43

rizona

-0.43

Gön

-0.43

InitVars

-0.42

POSITIVE LOGITS

########.

0.42

خواندن

0.37

 насељу

0.36

putan

0.33

Режи

0.32

脚注の使い方

0.32

fficio

0.32

SqlClient

0.31

 FontWeight

0.31

OleDb

0.31

Activations Density 0.105%

instances of uncertainty or inquiry about experiences or situations

common preceding words

No Comments

No Known Activations