INDEX

Explanations

terms and acronyms related to medical and biological research

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.1.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

AsUp

-0.69

уда

-0.61

Legături

-0.60

__':

-0.59

Ar

-0.58

posedge

-0.56

Архівовано

-0.55

Am

-0.54

 فريبيس

-0.54

IsPostBack

-0.53

POSITIVE LOGITS

 africaine

0.74

 barbati

0.72

 toluene

0.68

 Claudius

0.68

 cavitation

0.68

 propOrder

0.68

 carbonic

0.68

 diſt

0.67

 pulmonar

0.67

 ſub

0.65

Activations Density 0.838%

terms and acronyms related to medical and biological research

No Comments

No Known Activations