INDEX

Explanations

terms related to specific medical or scientific conditions and their implications

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.11.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

انيف

-0.63

NewUrlParser

-0.61

glGen

-0.60

 صوتيه

-0.60

 AppComponent

-0.60

NUMX

-0.58

 AppBar

-0.58

autoconfigure

-0.58

 المعيارى

-0.57

cerely

-0.56

POSITIVE LOGITS

Rohy

0.52

 latter

0.48

inya

0.46

いずれ

0.45

jooq

0.44

اصمة

0.44

 flavours

0.44

ürü

0.43

geb

0.42

 kaarangay

0.41

Activations Density 0.418%

terms related to specific medical or scientific conditions and their implications

No Comments

No Known Activations