INDEX

Explanations

references to software and code structures or implementations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.23.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

 location

-0.54

 situ

-0.50

 located

-0.46

sit

-0.44

はじめに

-0.43

ter

-0.41

located

-0.40

 localizado

-0.40

 micro

-0.40

saraba

-0.39

POSITIVE LOGITS

يميديا

0.84

TabIndex

0.81

AsUp

0.80

 Theſe

0.79

IntoConstraints

0.78

yntaxException

0.74

 فريبيس

0.71

StructEnd

0.70

 oprot

0.67

spesies

0.66

Activations Density 0.152%

references to software and code structures or implementations

No Comments

No Known Activations