INDEX

Explanations

specific programming environment details, including version numbers and software specifications

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

Versions of software, firmware, or builds

np_acts-logits-general · gemini-2.0-flash

build, version, infiltrate

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.18.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

 للاسماء

-0.60

VIAF

-0.52

hnia

-0.52

 Vann

-0.51

axs

-0.51

 createSprite

-0.50

AutoScale

-0.49

migrationBuilder

-0.48

ukkan

-0.48

wap

-0.48

POSITIVE LOGITS

 Theſe

0.79

 Majefty

0.74

 Monfieur

0.71

 Shakspeare

0.70

 itſelf

0.69

 myſelf

0.69

 Diſ

0.67

 ſeveral

0.66

 Anſ

0.66

 Houſe

0.65

Activations Density 0.248%

specific programming environment details, including version numbers and software specifications

Versions of software, firmware, or builds

build, version, infiltrate

No Comments

No Known Activations