INDEX

Explanations

sections of code with visual or formatting markers, indicating structured sections or comments in programming

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.8.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

 kaynağından

-0.60

hdashline

-0.57

 ведь

-0.56

awtextra

-0.56

 BorderRadius

-0.53

पया

-0.50

OutputType

-0.50

DataAnnotations

-0.49

 navíc

-0.49

RepeatedField

-0.48

POSITIVE LOGITS

出版年

0.78

################

0.74

////////////////

0.61

vantages

0.57

tencent

0.57

dirond

0.57

Tikang

0.56

躇

0.56

Schw

0.56

rovnik

0.55

Activations Density 0.199%

sections of code with visual or formatting markers, indicating structured sections or comments in programming

No Comments

No Known Activations