INDEX

Explanations

references to specific sites or locations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

 Lightboxes

-0.65

//

-0.59

ISTA

-0.54

rrrrr

-0.54

Hauptartikel

-0.54

nfc

-0.53

'>"

-0.53

BERRY

-0.53

itivo

-0.52

Katso

-0.52

POSITIVE LOGITS

 Sites

1.12

 sites

1.02

Sites

1.00

 SITE

0.97

 Site

0.94

 SITES

0.92

SITE

0.92

sites

0.85

Site

0.82

 site

0.76

Activations Density 0.095%

references to specific sites or locations

No Comments

No Known Activations