INDEX

Explanations

technical terms and concepts related to scientific studies and research findings

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

 defaultstate

-0.60

getMenuInflater

-0.60

AccessFile

-0.54

MessageOf

-0.53

 الرياضيه

-0.52

 GenerationType

-0.51

ytä

-0.51

 Chwiliwch

-0.50

 Wikiseite

-0.50

feinander

-0.50

POSITIVE LOGITS

 incidentally

0.59

 appunto

0.58

 autorytatywna

0.58

sizeCache

0.54

 admittedly

0.54

 duquel

0.53

SourceChecksum

0.52

bootstrapcdn

0.52

memoized

0.51

thâu

0.51

Activations Density 0.851%

technical terms and concepts related to scientific studies and research findings

No Comments

No Known Activations