INDEX

Explanations

references and citations to sources

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.15.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

LookAnd

-1.01

 AssemblyCulture

-0.94

yntaxException

-0.84

WebElementEntity

-0.83

 kasarigan

-0.83

 defaultstate

-0.78

writeFieldEnd

-0.75

GraphicsUnit

-0.75

GEBURTSDATUM

-0.71

fitrión

-0.70

POSITIVE LOGITS

 ویکی‌پدیای

0.57

www

0.56

www

0.55

 Wikipedia

0.49

 https

0.49

CNN

0.48

https

0.46

 unanimous

0.46

BBC

0.46

 wikipedia

0.45

Activations Density 0.117%

references and citations to sources

No Comments

No Known Activations

references and citations to sources

No Comments

No Known Activations