INDEX

Explanations

data types and type definitions used in programming

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

type or status identifiers

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.9.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

<bos>

-0.65

 snippetHide

-0.53

Šaltiniai

-0.45

Наводи

-0.44

 selera

-0.43

ч

-0.42

 prêtre

-0.41

⏜

-0.40

Revenir

-0.40

Rujuakan

-0.39

POSITIVE LOGITS

TYPE

1.79

 TYPE

1.17

TYPES

0.62

STATUS

0.62

tipo

0.59

 TYPES

0.57

ETYPE

0.55

TIPO

0.54

MODE

0.53

uxxxx

0.53

Activations Density 0.009%

data types and type definitions used in programming

type or status identifiers

No Comments

No Known Activations