INDEX

Explanations

references to identifiable entities or classifications within scientific or medical contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Rhestr

-0.42

 Real

-0.40

 real

-0.40

 memili

-0.38

Realtime

-0.36

 invading

-0.36

Real

-0.35

Beijo

-0.35

 Commissioner

-0.35

 Recommended

-0.34

POSITIVE LOGITS

+#+

0.63

 AssemblyCulture

0.62

URLException

0.60

MessageOf

0.56

########.

0.56

الحياه

0.55

WebElementEntity

0.54

mybatisplus

0.52

 referrerpolicy

0.52

0.50

Activations Density 0.334%

references to identifiable entities or classifications within scientific or medical contexts

No Comments

No Known Activations