INDEX

Explanations

markup tags and formatting elements in a document

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

Non-English text and code snippets

np_acts-logits-general · gemini-2.0-flash

code and markup closing tags

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

 мәкалә

-0.79

Personendaten

-0.78

########.

-0.77

BeginContext

-0.72

 \%$\\

-0.71

Tikang

-0.68

 IFTT

-0.68

inerja

-0.67

InjectAttribute

-0.67

Tazama

-0.66

POSITIVE LOGITS

</code>

0.64

 ujarnya

0.56

</em>

0.52

</tbody>

0.47

</tr>

0.47

omitempty

0.47

glEnd

0.45

 ucapnya

0.44

ynchronously

0.43

</i>

0.43

Activations Density 0.178%

markup tags and formatting elements in a document

Non-English text and code snippets

code and markup closing tags

No Comments

No Known Activations