INDEX

Explanations

textual identifiers and references, specifically discussing evidence and legal cases

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.2.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

 تضيفلها

-0.87

олові

-0.59

出版年

-0.55

tvguidetime

-0.55

UIControlState

-0.55

]]

-0.53

VIAF

-0.52

 utafitiHapana

-0.52

parsedMessage

-0.52

basicConfig

-0.52

POSITIVE LOGITS

InitVars

0.80

Kjelder

0.60

stak

0.53

かわらず

0.53

 encarga

0.51

.(*

0.50

Interment

0.50

stalt

0.50

 partitioning

0.50

iastes

0.49

Activations Density 1.597%

textual identifiers and references, specifically discussing evidence and legal cases

No Comments

No Known Activations