INDEX

Explanations

references to events, articles, or statements from various media sources

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.15.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

AnchorStyles

-0.73

 AssemblyCulture

-0.66

XmlAccessorType

-0.59

 👎

-0.58

ikkert

-0.58

 BorderRadius

-0.57

הערות

-0.56

TagHelper

-0.54

strijden

-0.54

rairie

-0.53

POSITIVE LOGITS

‘

0.67

'{@

0.64

0.63

new

0.60

‘

0.54

New

0.54

 Former

0.52

<bos>

0.51

New

0.50

脚注の使い方

0.50

Activations Density 0.066%

references to events, articles, or statements from various media sources

No Comments

No Known Activations