INDEX

Explanations

sections of text with no relevant content or activations

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

C++ or C# code snippets

np_acts-logits-general · gemini-2.0-flash

Korean War

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

minlength

-0.57

 endwhile

-0.53

 turned

-0.48

ou

-0.47

 vere

-0.46

 both

-0.44

 везе

-0.43

 turn

-0.43

POSITIVE LOGITS

IsContent

0.81

AutoScaleMode

0.81

 Theſe

0.77

tagHelperRunner

0.72

AutoScale

0.72

 "..\..\..\

0.71

IGraphics

0.71

 Signalez

0.70

 initComponents

0.69

IContainer

0.67

Activations Density 0.002%

sections of text with no relevant content or activations

C++ or C# code snippets

Korean War

No Comments

No Known Activations