INDEX

Explanations

occurrences of the word "set" in various forms and contexts

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

result set

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

 AssemblyCulture

-0.56

Symbolic

-0.46

Pablo

-0.46

تقاوى

-0.46

بوابة

-0.44

Gru

-0.43

@"/

-0.43

WEBPACK

-0.43

Gru

-0.42

 IBOutlet

-0.42

POSITIVE LOGITS

ResultSet

1.65

 ResultSet

1.44

 resultSet

1.13

resultSet

1.00

TypedDataSet

0.78

ExecuteReader

0.76

executeQuery

0.71

rset

0.59

 ſes

0.54

 resultat

0.53

Activations Density 0.001%

occurrences of the word "set" in various forms and contexts

result set

No Comments

No Known Activations