INDEX

Explanations

references to various topics and their coverage in discussions or writings

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

followed by "topic" or "topics"

np_acts-logits-general · gemini-2.0-flash

discussing topics or subjects

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

UserScript

-0.55

 дописавши

-0.55

nologue

-0.51

Ử

-0.51

струкция

-0.51

ombic

-0.50

перь

-0.49

 RoutedEventArgs

-0.49

buttonBar

-0.49

migrationBuilder

-0.47

POSITIVE LOGITS

 topic

3.35

 topics

3.04

 subject

2.98

 Topic

2.75

Topic

2.61

 subjects

2.60

 theme

2.48

subject

2.48

topic

2.47

 Topics

2.44

Activations Density 0.484%

references to various topics and their coverage in discussions or writings

followed by "topic" or "topics"

discussing topics or subjects

No Comments

No Known Activations