INDEX

Explanations

specific nouns related to processes, roles, or measurements within various contexts

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

specific nouns

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

Castle

-0.56

Don

-0.48

 Castle

-0.47

RETT

-0.47

 Spagna

-0.47

Something

-0.46

Don

-0.46

Basic

-0.45

retten

-0.45

aries

-0.45

POSITIVE LOGITS

IntoConstraints

0.63

AndEndTag

0.61

 ब्रेकडाउन

0.52

PreInfinity

0.49

-------

0.48

TagMode

0.48

BeginContext

0.48

HostException

0.46

 arşivlendi

0.44

 useStyles

0.44

Activations Density 0.074%

specific nouns related to processes, roles, or measurements within various contexts

specific nouns

No Comments

No Known Activations