INDEX

Explanations

attributes related to abilities or transformations in a specific context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.17.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

脚注の使い方

-0.76

 שוליים

-0.70

 kasarigan

-0.69

providedIn

-0.65

 alluminio

-0.63

onViewCreated

-0.59

 škoda

-0.57

 insuffisamment

-0.56

ckså

-0.55

PerformLayout

-0.52

POSITIVE LOGITS

 increase

0.78

 invul

0.75

 increased

0.70

 boost

0.69

 cure

0.67

 improved

0.66

 immunity

0.65

 Increase

0.64

 invincible

0.64

 увели

0.61

Activations Density 0.404%

attributes related to abilities or transformations in a specific context

No Comments

No Known Activations