INDEX

Explanations

HTML tags, specifically bold and italic formatting

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

</em>

-1.41

</strong>

-1.39

 يتيمه

-1.24

 propOrder

-1.17

",@"

-1.16

<em>

-1.11

<strong>

-1.10

ﬂ

-1.09



-1.09

ﬂ

-1.05

POSITIVE LOGITS

</b>

1.87

</i>

1.66

<i>

1.21

<b>

1.21

dfrac

1.20

َّ

0.92

±

0.89

 Helena

0.85

 Prussian

0.85

'>

0.83

Activations Density 0.045%

HTML tags, specifically bold and italic formatting

No Comments

No Known Activations