INDEX

Explanations

the introduction or mention of new topics or subjects in a document

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

 kesi

-0.60

TagMode

-0.59

 udaler

-0.59

الحياه

-0.59

 privée

-0.58

 Económica

-0.57

 NACIONAL

-0.54

SourceChecksum

-0.54

RTLI

-0.54

 Inscrivez

-0.53

POSITIVE LOGITS

archiviato

0.60

Przypisy

0.55

帖最后由

0.54

fillType

0.54

findpost

0.53

 nakalista

0.53

0.52

twimg

0.51

//

0.51

 importantly

0.51

Activations Density 0.283%

the introduction or mention of new topics or subjects in a document

No Comments

No Known Activations