INDEX

Explanations

terminology related to legal and statistical status

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

__':

-0.72

status

-0.72

SourceChecksum

-0.72

stated

-0.71

Staff

-0.70

 Staff

-0.69

staff

-0.68

 STAFF

-0.67

 staff

-0.67

 static

-0.66

POSITIVE LOGITS

quo

0.86

Quo

0.71

 epileptic

0.52

квар

0.50

quo

0.50

holders

0.50

 noqa

0.50

grafo

0.49

дарт

0.47

 unequiv

0.46

Activations Density 0.467%

terminology related to legal and statistical status

No Comments

No Known Activations