INDEX

Explanations

terms related to scientific measurements and variables in equations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_10/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.10.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

findpost

-0.86

IDATE

-0.86

 Bateman

-0.85

lamabad

-0.84

 kaynağından

-0.83

 Willard

-0.81

skull

-0.80

COW

-0.78

躇

-0.77

RenderAtEndOf

-0.77

POSITIVE LOGITS

Mu

0.79

Muh

0.78

mu

0.78

Muh

0.78

Somebody

0.74

autogui

0.73

Mu

0.69

 JsonResponse

0.67

mu

0.67

 Overton

0.67

Activations Density 0.829%

terms related to scientific measurements and variables in equations

No Comments

No Known Activations