INDEX

Explanations

abbreviations and acronyms related to scientific terms and measurements

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

GEBURTSDATUM

-0.61

LookAnd

-0.60

principalTable

-0.58

oredCriteria

-0.57

principalColumn

-0.56

MessageOf

-0.56

BASELINE

-0.53

 propOrder

-0.51

CreateIndex

-0.49

Manbalar

-0.49

POSITIVE LOGITS

 BoxFit

0.70

MethodManager

0.65

 surla

0.63

Tikang

0.61

 useStyles

0.60

 createSlice

0.57

CHAFT

0.56

 ProgressDialog

0.55

TargetApi

0.55

titleMargin

0.55

Activations Density 1.882%

abbreviations and acronyms related to scientific terms and measurements

No Comments

No Known Activations