INDEX

Explanations

references to confusion or disarray

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 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

ScopeManager

-0.58

oa̍t

-0.58

meyen

-0.58

 mxArray

-0.57

stateProvider

-0.57

 nakalista

-0.53

not

-0.49

Voici

-0.49

the

-0.49

 quang

-0.48

POSITIVE LOGITS

✨:

0.94

Huo

0.76

 geografic

0.75

QMetaType

0.74

 Cæsar

0.73

 Participating

0.72

fjspx

0.71

=$?

0.71

Sqft

0.71

Participating

0.71

Activations Density 0.222%

references to confusion or disarray

No Comments

No Known Activations