INDEX

Explanations

references to specific titles or formal names

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

Code or formal language snippets

np_acts-logits-general · gemini-2.0-flash

legal and technical terms

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.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

</i>

-1.37

</code>

-0.83

</b>

-0.81

</h6>

-0.77

</th>

-0.76

</td>

-0.74

&#

-0.65

<b>

-0.62

-0.60

--

-0.60

POSITIVE LOGITS

adaptiveStyles

1.21

AddTagHelper

1.16

SourceChecksum

1.08

 kohdetta

0.96

TagMode

0.94

MigrationBuilder

0.93

 actionMode

0.93

يكب

0.91

AntiForgeryToken

0.90

millimeters

0.88

Activations Density 0.055%

references to specific titles or formal names

Code or formal language snippets

legal and technical terms

No Comments

No Known Activations