INDEX

Explanations

references to support in research or community contributions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.18.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

tagHelperRunner

-0.55

<eos>

-0.52

jdt

-0.46

 Either

-0.46

}>{

-0.46

Either

-0.46

">'+

-0.45

Those

-0.45

ようになります

-0.45

">{

-0.44

POSITIVE LOGITS

TagMode

0.84

ArrowToggle

0.84

 ISNI

0.74

RenderAtEndOf

0.73

parsedMessage

0.72

RegistryLite

0.71

 estekak

0.68

windowFixed

0.67

UnsafeEnabled

0.67

 <=",

0.65

Activations Density 0.050%

references to support in research or community contributions

No Comments

No Known Activations