INDEX

Explanations

programming constructs and syntax elements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.9.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

omock

-0.70

<bos>

-0.69

כשיו

-0.67

pleaños

-0.64

kegaard

-0.62

PreferredItem

-0.61

 Langu

-0.60

 betweenstory

-0.59

inkov

-0.59

estacks

-0.58

POSITIVE LOGITS

antMatchers

0.71

HasIndex

0.67

styleType

0.66

TagHelpers

0.60

Bronnen

0.58

 folle

0.55

eqn

0.55

styleUrls

0.53

tagHelperRunner

0.53

 Wicidata

0.53

Activations Density 0.013%

programming constructs and syntax elements

No Comments

No Known Activations