INDEX

Explanations

Spanish or French articles and numbers indicating quantity

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

 suivantes

-0.88

 nationaux

-0.76

tă

-0.70

 armée

-0.69

 suivants

-0.66

 restantes

-0.66

er

-0.65

 înainte

-0.63

 nemus

-0.63

ásra

-0.63

POSITIVE LOGITS

{}",

1.06

}")

0.93

एक

0.93

"")

0.93

"):

0.92

 Một

0.91

')

0.91

Une

0.90

"){

0.90

'):

0.90

Activations Density 0.015%

Spanish or French articles and numbers indicating quantity

No Comments

No Known Activations