INDEX

Explanations

numeric identifiers or statistics related to scores and accomplishments in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.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

 sérieux

-0.56

 perpé

-0.52

 مشين

-0.52

 destinées

-0.48

 autant

-0.45

 Gutes

-0.45

RegistryLite

-0.45

==",

-0.44

 nomme

-0.44

quilibrium

-0.44

POSITIVE LOGITS

 EClass

0.71

SourceChecksum

0.68

ibouti

0.67

RefNanny

0.65

WindowConstants

0.64

SerializedSize

0.62

 ***!

0.62

inthe

0.62

 recenti

0.60

 linkovi

0.59

Activations Density 0.683%

numeric identifiers or statistics related to scores and accomplishments in various contexts

No Comments

No Known Activations