INDEX

Explanations

specific programming terms and data structure keywords

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.1.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

 runner

-0.52

ficamente

-0.50

webElementXpaths

-0.50

 Administrativna

-0.49

runner

-0.48

EXERC

-0.47

 reservados

-0.45

燐

-0.45

сторія

-0.45

 shower

-0.45

POSITIVE LOGITS

ScopeManager

0.73

Personensuche

0.70

findpost

0.69

ⓧ

0.66

 stub

0.63

 Severity

0.63

ecco

0.63

 IndexPath

0.62

 Stub

0.62

تقاوى

0.61

Activations Density 2.303%

specific programming terms and data structure keywords

No Comments

No Known Activations