INDEX

Explanations

structured data related to shows and episodes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.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

ssaint

-0.50

 though

-0.48

<bos>

-0.45

ogados

-0.44

MENAFN

-0.44

 Voraussetzung

-0.44

NonNull

-0.42

though

-0.42

 prosím

-0.41

 poichè

-0.40

POSITIVE LOGITS

RenderAtEndOf

0.83

 незавершена

0.66

@__

0.64

AndEndTag

0.64

StoryboardSegue

0.61

setof

0.60

 MISCELLANEOUS

0.60

abestanden

0.59

 unnamed

0.59

Unnamed

0.58

Activations Density 0.725%

structured data related to shows and episodes

No Comments

No Known Activations