INDEX

Explanations

terms related to guidelines, structural quality, or specifications in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.9.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

+#+#

-0.76

 فريبيس

-0.70

DeleteBehavior

-0.68

 numberOfRows

-0.65

WebVitals

-0.60

 AssemblyTitle

-0.58

 nahilalakip

-0.55

PathVariable

-0.55

principalTable

-0.53

parsedMessage

-0.53

POSITIVE LOGITS

 TextAppearance

0.64

참고

0.59

 Hiller

0.54

étaient

0.52

RegressionTest

0.52

 anthology

0.52

*);

0.52

ⓧ

0.51

*>

0.50

*)

0.49

Activations Density 1.085%

terms related to guidelines, structural quality, or specifications in various contexts

No Comments

No Known Activations