INDEX

Explanations

instances of questions and assertions of knowledge

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

VersionUID

-0.59

 Littleton

-0.59

databind

-0.57

IsContent

-0.56

țiilor

-0.55

worms

-0.55

protoimpl

-0.55

Ỗ

-0.54

 Guille

-0.53

 Lucinda

-0.53

POSITIVE LOGITS

 חיצוניים

0.79

KURZBESCHREIBUNG

0.73

Rhestr

0.65

)_/¯

0.62

 مشين

0.61

AnchorTagHelper

0.58

IntoConstraints

0.58

 CURIAM

0.57

 localObject

0.57

 tropicales

0.55

Activations Density 0.074%

instances of questions and assertions of knowledge

No Comments

No Known Activations