INDEX

Explanations

phrases that indicate high popularity or acclaim

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.9.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

 Geschmack

-0.54

 Équipe

-0.51

ādā

-0.51

 canoes

-0.51

ilead

-0.49

 brasili

-0.49

 stadion

-0.48

 zade

-0.48

 Erskine

-0.48

bion

-0.48

POSITIVE LOGITS

 nakalista

1.11

 snippetHide

0.79

enumi

0.78

\{\\

0.75

+#+

0.75

✨:

0.72

ViewFeatures

0.70

findpost

0.70

glGen

0.68

insics

0.67

Activations Density 0.102%

phrases that indicate high popularity or acclaim

No Comments

No Known Activations

phrases that indicate high popularity or acclaim

No Comments

No Known Activations