INDEX

Explanations

references to other sections or notes within the document

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

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

+:+

-0.56

("")]

-0.53

tojas

-0.48

ogne

-0.47

mybatisplus

-0.46

Da

-0.44

Hozzáférés

-0.44

ţional

-0.44

OUNT

-0.43

REME

-0.43

POSITIVE LOGITS

](#

0.87

 myſelf

0.83

 cref

0.83

 fubject

0.80

 purpoſe

0.74

 raiſ

0.72

writeFieldEnd

0.69

PerformLayout

0.69

 poffible

0.68

GraphicsUnit

0.67

Activations Density 1.045%

references to other sections or notes within the document

No Comments

No Known Activations