INDEX

Explanations

references to mathematical models and concepts within data analysis or scientific contexts

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

Mathematical or chemical notation

np_acts-logits-general · gemini-2.0-flash

names and places

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.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

 Adel

-0.89

 Solano

-0.76

 Shih

-0.75

Adel

-0.74

 Amarillo

-0.72

 Vanessa

-0.72

 Seward

-0.71

MethodManager

-0.71

 kaban

-0.70

 Garrett

-0.69

POSITIVE LOGITS

 Morris

0.77

Morris

0.71

Jim

0.70

morris

0.62

 Morrissey

0.62

 Château

0.59

 Murphy

0.59

 Chateau

0.59

 Thor

0.58

Jim

0.58

Activations Density 0.693%

references to mathematical models and concepts within data analysis or scientific contexts

Mathematical or chemical notation

names and places

No Comments

No Known Activations