INDEX

Explanations

code-related keywords and actions within programming contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ValueStyle

-1.02

awtextra

-0.80

SharedCtor

-0.78

ExecuteReader

-0.77

脚注の使い方

-0.76

CloseOperation

-0.76

stateProvider

-0.76

 estekak

-0.75

FunctionFlags

-0.73

 onAnimation

-0.72

POSITIVE LOGITS

PyExc

0.59

 libraries

0.47

 extensão

0.45

usepackage

0.45

methodName

0.44

 lát

0.44

 فن

0.43

فن

0.42

 toolkit

0.42

库

0.42

Activations Density 0.326%

code-related keywords and actions within programming contexts

No Comments

No Known Activations