INDEX

Explanations

software-related terms and references within code snippets

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

CppMethod

-0.73

 consultato

-0.72

setVerticalGroup

-0.65

 onAnimation

-0.59

ViewStyle

-0.58

RectangleBorder

-0.58

참고

-0.58

ntax

-0.57

rouvez

-0.57

OGND

-0.57

POSITIVE LOGITS

 jsPsych

0.84

formik

0.61

zzleHttp

0.58

PMailer

0.58



0.56

sequelize

0.56

astify

0.55

0.53

 AutoMapper

0.52

 useHistory

0.51

Activations Density 0.407%

software-related terms and references within code snippets

No Comments

No Known Activations