INDEX

Explanations

detailed references and citations in academic writing

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

AsUp

-0.73

providedIn

-0.72

RuleContext

-0.55

جغرافيا

-0.55

 CallOverrides

-0.54

TagHelper

-0.53

 <=",

-0.53

HideFlags

-0.53

chließ

-0.52

<sub>

-0.51

POSITIVE LOGITS

0.70

\&

0.62

\\

0.57

\\

0.57

?\\

0.56

BibitemShut

0.55

\{\

0.55

 Jungfrau

0.54

."</

0.54

;\\

0.51

Activations Density 0.002%

detailed references and citations in academic writing

No Comments

No Known Activations