INDEX

Explanations

programming-related keywords and function calls

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Réponses

-0.44

<eos>

-0.41

☸

-0.37

źć

-0.37

wirkung

-0.36

 Sequo

-0.35

 wenden

-0.35

 phủ

-0.35

 obra

-0.35

↵↵

-0.34

POSITIVE LOGITS

ArgsConstructor

0.77

 فريبيس

0.73

رشف

0.72

DBNull

0.71

клопе

0.70

RetentionPolicy

0.69

+#+#

0.69

 Meksiku

0.68

URLException

0.67

matchCondition

0.67

Activations Density 2.464%

programming-related keywords and function calls

No Comments

No Known Activations