INDEX

Explanations

clinical terms and concepts related to medical studies and procedures

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

Tokens starting with "Cla" or "Kla"

np_acts-logits-general · gemini-2.0-flash

clin, clap, kla prefixes

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

 مشين

-0.89

期刊论文

-0.84

**/

-0.81

InSection

-0.80

__":

-0.80

 commerciali

-0.79

__':

-0.78

tagHelperRunner

-0.76

SerializeField

-0.75

oneofs

-0.74

POSITIVE LOGITS

Kla

1.08

Cla

1.01

Kl

1.00

cl

0.99

cla

0.97

Cla

0.97

Cl

0.94

 Klon

0.92

CL

0.91

CLA

0.91

Activations Density 0.368%

clinical terms and concepts related to medical studies and procedures

Tokens starting with "Cla" or "Kla"

clin, clap, kla prefixes

No Comments

No Known Activations