INDEX

Explanations

functions related to graphical representations and interpretations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_0/width_16k/average_l0_129

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

Personensuche

-0.66

migrationBuilder

-0.55

featureID

-0.54

Rüyada

-0.54

:✨

-0.52

はじめに

-0.52

contentLoaded

-0.50

 препратки

-0.48

ScopeManager

-0.47

 الحره

-0.47

POSITIVE LOGITS

 interpret

0.72

 interpretation

0.65

 Interpret

0.65

parsed

0.63

 parsed

0.63

Interpret

0.62

interpretation

0.61

 interpretive

0.60

 Interpretation

0.60

interpret

0.60

Activations Density 0.163%

functions related to graphical representations and interpretations

No Comments

No Known Activations