INDEX

Explanations

HTML tags, particularly bold and italicized elements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

</em>

-1.42

</strong>

-1.40

 يتيمه

-1.17

<em>

-1.07



-1.07

<strong>

-1.07

",@"

-1.07

ﬂ

-1.05

ﬂ

-1.02

 propOrder

-1.01

POSITIVE LOGITS

</b>

1.84

</i>

1.63

dfrac

1.24

<i>

1.23

<b>

1.21

±

0.95

َّ

0.91

0.89

 Prussian

0.88

 Wals

0.88

Activations Density 0.062%

HTML tags, particularly bold and italicized elements

No Comments

No Known Activations