INDEX

Explanations

terms related to clinical and medical abbreviations or measurements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_17/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.17.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

 onAnimation

-0.57

 userSchema

-0.57

InputBorder

-0.54

 onCreateView

-0.54

ffffffff

-0.51

 façons

-0.51

 actionMode

-0.50

 Touchable

-0.50

 onPostExecute

-0.50

 PASSWORD

-0.49

POSITIVE LOGITS

++)

0.72

 PSOE

0.69

 СПб

0.65

 NYPD

0.65

MD

0.65

GOTREF

0.64

featureID

0.64

MS

0.63

Rptr

0.62

MLB

0.61

Activations Density 1.378%

terms related to clinical and medical abbreviations or measurements

No Comments

No Known Activations