INDEX

Explanations

elements that indicate comparisons or assignments in code

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

 FetchType

-0.54

ativna

-0.50

keySet

-0.46

gpl

-0.45

flas

-0.42

zień

-0.42

 flas

-0.42

Flas

-0.42

SUS

-0.42

<>

-0.41

POSITIVE LOGITS

InputBorder

0.83

Tembelea

0.83

EndInit

0.78

 resourceCulture

0.78

InjectAttribute

0.73

клопе

0.70

WebElementEntity

0.64

 EconPapers

0.61

 économies

0.60

BeginContext

0.59

Activations Density 0.119%

elements that indicate comparisons or assignments in code

No Comments

No Known Activations