INDEX

Explanations

references to regulatory agencies and their functions

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

groups and locations

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

 viewType

-0.39

artifactId

-0.39

いただけ

-0.36

 getchar

-0.35

 momentan

-0.33

ChatColor

-0.33

 Kämp

-0.32

 Severity

-0.32

physician

-0.32

chin

-0.32

POSITIVE LOGITS

BeginContext

0.66

ſelves

0.56

 gynhyrchwyd

0.54

oredCriteria

0.53

 CanadaChoose

0.53

OGND

0.52

 PeEnEo

0.52

 AppCompatTheme

0.52

 OMITBAD

0.51

rsiniz

0.49

Activations Density 0.026%

references to regulatory agencies and their functions

groups and locations

No Comments

No Known Activations