INDEX

Explanations

terms related to medical diagnoses and conditions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.10.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

TagMode

-0.65

dafx

-0.54

EndContext

-0.53

 meilleures

-0.53

estanding

-0.52

 suất

-0.51

 meilleurs

-0.51

 webbplats

-0.49

epam

-0.49

 migliori

-0.48

POSITIVE LOGITS

RenderAtEndOf

0.74

DoubleQuotes

0.65

 appeared

0.58

 appears

0.56

 strange

0.56

 resembling

0.56

?):

0.55

 seemed

0.54

 appear

0.54

 похоже

0.54

Activations Density 0.412%

terms related to medical diagnoses and conditions

No Comments

No Known Activations