INDEX

Explanations

the term "is" used in various contexts, indicating definitions or states of being

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

"What is the"

np_acts-logits-general · gemini-2.0-flash

mathematical sequence term queries

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

-0.98

-0.88

-0.86

↵↵

-0.84

-0.83

-0.82

-0.81

-0.80

POSITIVE LOGITS

RenderAtEndOf

1.96

 ujednoznacz

1.78

tagHelperRunner

1.76

MigrationBuilder

1.70

ValueStyle

1.66

rungsseite

1.65

 autorytatywna

1.57

uxxxx

1.57

DockStyle

1.56

 مشين

1.55

Activations Density 0.617%

the term "is" used in various contexts, indicating definitions or states of being

"What is the"

mathematical sequence term queries

No Comments

No Known Activations