INDEX

Explanations

references to programs and their descriptions

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

program and variations

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

 graffiti

-0.41

ейчас

-0.40

ituaries

-0.38

чется

-0.38

 defiance

-0.38

spesies

-0.38

ovatel

-0.37

 vigilance

-0.37

makeConstraints

-0.36

 angekommen

-0.36

POSITIVE LOGITS

 program

1.08

 programme

1.05

programme

0.96

program

0.94

 Programme

0.94

 Program

0.92

 Programm

0.90

Program

0.88

Programme

0.88

 programs

0.88

Activations Density 0.231%

references to programs and their descriptions

program and variations

No Comments

No Known Activations