INDEX

Explanations

technical and scientific terms related to medical and engineering contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/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.13.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

 RouterModule

-0.47

டைய

-0.43

UMB

-0.43

 discul

-0.43

λους

-0.42

 vice

-0.42

{{/

-0.42

 spodnie

-0.42

 "'");

-0.42

aga

-0.41

POSITIVE LOGITS

NameInMap

0.81

BeginContext

0.70

Gambas

0.69

etc

0.68

 мәкал

0.65

contentLoaded

0.64

kháu

0.63

rrggbb

0.63

 gynhyrchwyd

0.63

 <<<<<<<<<<<<<<

0.63

Activations Density 0.630%

technical and scientific terms related to medical and engineering contexts

No Comments

No Known Activations