INDEX

Explanations

long-term medical terms and their implications

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

 schnell

-0.54

tsburgh

-0.53

classnames

-0.53

 rasch

-0.52

 المعيارى

-0.51

 soon

-0.50

anderson

-0.49

quickly

-0.49

enix

-0.48

 segera

-0.48

POSITIVE LOGITS

ago

0.90

 NSCoder

0.74

 hinweg

0.73



0.66

(>

0.64

espan

0.63

 commitment

0.62

 viability

0.62

ingly

0.62

SBATCH

0.60

Activations Density 0.182%

long-term medical terms and their implications

No Comments

No Known Activations