INDEX

Explanations

references to medical procedures and studies

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.23.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

 ſtate

-0.72

 propOrder

-0.70

 raiſ

-0.66

 myſelf

-0.62

 otomatig

-0.62

Efq

-0.62

 purpoſe

-0.61

 Houſe

-0.61

 pleaſure

-0.61

ulemon

-0.61

POSITIVE LOGITS

 referral

0.61

 casualty

0.56

 private

0.55

 government

0.54

 Referral

0.51

 Government

0.51

government

0.50

Government

0.49

 specialist

0.48

 Apollo

0.48

Activations Density 0.266%

references to medical procedures and studies

No Comments

No Known Activations