INDEX

Explanations

acronyms and abbreviations related to medical and scientific concepts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_10/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.10.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

 المعيارى

-1.07

 snippetHide

-0.91

 nahilalakip

-0.90

RenderAtEndOf

-0.88

 дописавши

-0.85

 disambiguazione

-0.84

Portale

-0.80

 Paglinawan

-0.80

 חיצוניים

-0.79

ญิง

-0.77

POSITIVE LOGITS

เส

0.52

 nepř

0.50

clerview

0.48

 rör

0.45

 fær

0.43

ijs

0.43

{'

0.42

Is

0.41

สม

0.41

Activations Density 1.783%

acronyms and abbreviations related to medical and scientific concepts

No Comments

No Known Activations