INDEX

Explanations

numeric identifiers and specific terms related to film and military contexts

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

mention of practices case

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

 onAnimation

-0.58

 ſtate

-0.56

makeConstraints

-0.55

 dieſe

-0.54

 ſta

-0.53

 queſta

-0.53

 müſſen

-0.52

 ſehr

-0.51

 ſchon

-0.51

iſche

-0.51

POSITIVE LOGITS

ScopeManager

0.42

OGND

0.32

IsMutable

0.30

 ExecuteAsync

0.30

ally

0.28

ẵn

0.27

AutoField

0.26

 Edward

0.26

ugier

0.26

 OMITBAD

0.26

Activations Density 0.037%

numeric identifiers and specific terms related to film and military contexts

mention of practices case

No Comments

No Known Activations