INDEX

Explanations

content related to medical terminology or conditions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.14.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

 >=",

-0.58

 defaultstate

-0.55

 AssemblyCulture

-0.52

Dro

-0.49

 grind

-0.49

dro

-0.48

msgSender

-0.48

LookAnd

-0.47

Dro

-0.47

 Gran

-0.47

POSITIVE LOGITS

ⓧ

0.85

 InputDecoration

0.72

 تانيه

0.71

KommentareTeilen

0.70

apnews

0.68

商品説明

0.64

 createSlice

0.63

StoryboardSegue

0.63

 firebaseConfig

0.62

ècie

0.61

Activations Density 0.394%

content related to medical terminology or conditions

No Comments

No Known Activations