INDEX

Explanations

non-informative or empty content in the text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_6/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.6.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

ers

-0.67

anelli

-0.66

er

-0.62

ing

-0.61

 inne

-0.60

“

-0.59

чет

-0.58

제

-0.58

 South

-0.57

 vers

-0.57

POSITIVE LOGITS

 }}$}

1.16

]")]

1.15

ագրություններ

1.14

󠁿

1.06

 Taktlose

0.97

$)$

0.96

.³

0.95

}{*}{}

0.94

--}}

0.92

 Audiodateien

0.91

Activations Density 0.161%

non-informative or empty content in the text

No Comments

No Known Activations