INDEX

Explanations

references to medical conditions and complications

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

 Monthly

-0.52

Hunter

-0.51

 monat

-0.51

esine

-0.50

Monthly

-0.50

kap

-0.50

monthly

-0.49

zema

-0.49

ULE

-0.49

udit

-0.48

POSITIVE LOGITS

Efq

0.84

 itſelf

0.72

AndEndTag

0.72

 himſelf

0.71

bootstrapcdn

0.71

 myſelf

0.70

 hospital

0.70

InjectAttribute

0.70

ſelf

0.69

 sepsis

0.68

Activations Density 0.705%

references to medical conditions and complications

No Comments

No Known Activations

references to medical conditions and complications

No Comments

No Known Activations