INDEX

Explanations

terms related to mental and physical conditions, specifically their effects and measurements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.14.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

 resourceCulture

-0.72

webElementXpaths

-0.65

 ***!

-0.64

AddTagHelper

-0.60

 صوتيه

-0.55

 HasFactory

-0.53

 kaarangay

-0.53

 Signalez

-0.53

 PARTE

-0.53

Hentet

-0.50

POSITIVE LOGITS

انجليز

0.55

 Beatrix

0.54

 särskilt

0.50

upuesto

0.49

 ensu

0.49

ранее

0.49

これに

0.48

 Sedangkan

0.48

lapsingToolbar

0.48

creen

0.47

Activations Density 0.478%

terms related to mental and physical conditions, specifically their effects and measurements

No Comments

No Known Activations