INDEX

Explanations

biomedical terminology and specific categorizations related to biological and medical terms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Winaray

-0.76

declarations

-0.75

 Italijani

-0.75

nościo

-0.66

RTEX

-0.64

 tartalomajánló

-0.64

bootstrapcdn

-0.63

ApiModelProperty

-0.62

 AppColors

-0.60

actionMode

-0.60

POSITIVE LOGITS

 nhiêu

0.82

Hentet

0.69

 bArr

0.67

tiful

0.60

ioutil

0.59

BPS

0.59

 Basics

0.56

BCS

0.56

voorbeeld

0.55

BEM

0.55

Activations Density 1.630%

biomedical terminology and specific categorizations related to biological and medical terms

No Comments

No Known Activations