INDEX

Explanations

structures and symbols used in scientific or technical writing

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.11.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

Viitteet

-0.59

 AspNetCore

-0.54

IsMutable

-0.53

ArgsConstructor

-0.49

BeginInit

-0.47

{?>

-0.46

 apron

-0.45

StoryboardSegue

-0.45

MOQ

-0.45

GIH

-0.45

POSITIVE LOGITS

<bos>

0.67

colgroup

0.66

 Schmitz

0.62

 CGRectMake

0.60

mybatisplus

0.59

DidChange

0.57

]--;

0.54

Pyx

0.54

boer

0.53

Према

0.53

Activations Density 1.582%

structures and symbols used in scientific or technical writing

No Comments

No Known Activations