INDEX

Explanations

terms related to scientific and medical contexts, specifically regarding compounds and their properties

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

 defaultstate

-0.74

 незавершена

-0.67

醐

-0.65

<?

-0.64

EDEFAULT

-0.61

httphttps

-0.60

 cutest

-0.60

 edildi

-0.59

zzleHttp

-0.59

 besoins

-0.58

POSITIVE LOGITS

uda

0.70

udos

0.65

UDA

0.64

UD

0.59

EndTag

0.58

 Aviv

0.55

ud

0.55

Ze

0.53

udo

0.52

 ảo

0.52

Activations Density 2.323%

terms related to scientific and medical contexts, specifically regarding compounds and their properties

No Comments

No Known Activations