INDEX

Explanations

references to mice and mouse-related actions in various contexts

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

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

 ویکی‌پدی

-0.63

WriteTagHelper

-0.57

MMdd

-0.56

-0.54

ValueStyle

-0.54

tonsoft

-0.53

WithMany

-0.52

AutoresizingMask

-0.50

uarts

-0.50

PLEX

-0.50

POSITIVE LOGITS

 Mice

0.94

 MOUSE

0.92

 mice

0.89

 Mouse

0.84

mice

0.81

Mice

0.81

 rodents

0.80

 mouse

0.78

 cursor

0.76

🐭

0.74

Activations Density 0.125%

references to mice and mouse-related actions in various contexts

No Comments

No Known Activations