INDEX

Explanations

method return statements and variable assignments

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

 ujednoznacz

-0.83

 مرئيه

-0.75

 estimés

-0.73

Enllaces

-0.71

findpost

-0.71

ंदीखरीदारी

-0.70

FunctionFlags

-0.70

RectangleBorder

-0.69

 跳转至

-0.68

WriteLiteral

-0.67

POSITIVE LOGITS

ngdoc

0.62

migrationBuilder

0.56

OrBuilder

0.45

checkable

0.43

IEnumerator

0.43

ServletConfig

0.43

ruk

0.42

Autowired

0.41

nage

0.41

tric

0.40

Activations Density 0.027%

method return statements and variable assignments

No Comments

No Known Activations