INDEX

Explanations

references to legal or regulatory contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.11.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

 NSCoder

-0.83

 ujednoznacz

-0.82

 otomatig

-0.78

CloseOperation

-0.77

 propOrder

-0.74

 समीक्षक

-0.70

WriteTagHelper

-0.66

principalTable

-0.65

FormTagHelper

-0.65

رشف

-0.64

POSITIVE LOGITS

 displaying

0.54

 badges

0.54

esomeness

0.53

 conveying

0.50

 display

0.49

classnames

0.49

snprintf

0.48

égories

0.48

boxed

0.47

THEW

0.47

Activations Density 0.272%

references to legal or regulatory contexts

No Comments

No Known Activations