INDEX

Explanations

references to medical conditions, symptoms, and their associated treatments or contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_6/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.6.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

Демографія

-0.68

 nahilalakip

-0.66

SharedDtor

-0.66

lapsingToolbar

-0.66

 propOrder

-0.62

ItemLayout

-0.61

 Meksiku

-0.61

 esternos

-0.57

preet

-0.55

HtmlAttribute

-0.55

POSITIVE LOGITS

subpackage

0.63

 ordinaire

0.51

 getItemCount

0.50

 humain

0.49

⏟

0.46

borderSide

0.46

 humaine

0.46

 such

0.45

OOTDTY

0.45

judice

0.44

Activations Density 1.471%

references to medical conditions, symptoms, and their associated treatments or contexts

No Comments

No Known Activations