INDEX

Explanations

parameters, settings, or configurations within a technical document

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

原始内容存档于

-0.38

 bête

-0.38

zont

-0.38

mogat

-0.37

 traduire

-0.36

 suivant

-0.36

 hany

-0.35

__((

-0.35

 aérienne

-0.34

ToAdd

-0.34

POSITIVE LOGITS

UrlResolution

0.97

EndProject

0.91

OGND

0.90

رشف

0.89

Tikang

0.85

 '\\;'

0.83

IVEREF

0.79

 mergeFrom

0.78

featureID

0.77

 StringTokenizer

0.76

Activations Density 1.233%

parameters, settings, or configurations within a technical document

No Comments

No Known Activations