INDEX

Explanations

terminology and concepts related to programming and software development

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

mathematical or typesetting markup

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

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

 surla

-0.84

 Geſch

-0.84

TagMode

-0.81

 beſte

-0.78

 مرئيه

-0.77

AnchorTagHelper

-0.77

 ſei

-0.77

queryInterface

-0.77

 ſind

-0.76

 فريبيس

-0.76

POSITIVE LOGITS

0.39

0.37

<tbody>

0.36

0.35

<eos>

0.35

0.34

ason

0.34

0.33

：

0.33

Activations Density 0.000%

terminology and concepts related to programming and software development

mathematical or typesetting markup

No Comments

No Known Activations