INDEX

Explanations

references to locations or geographical terms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.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

RectangleBorder

-1.08

SharedDtor

-0.78

ConstraintMaker

-0.76

Personendaten

-0.74

 للاسماء

-0.69

StoryboardSegue

-0.68

Geplaatst

-0.68

BuildContext

-0.68

 EdgeInsets

-0.67

脚注の使い方

-0.66

POSITIVE LOGITS

eski

0.47

 impar

0.44

 milli

0.39

killer

0.38

cum

0.38

ord

0.37

contentLoaded

0.36

 kamu

0.36

kent

0.36

 Mill

0.36

Activations Density 0.033%

references to locations or geographical terms

No Comments

No Known Activations