INDEX

Explanations

references to devices and their specifications, particularly in relation to size and functions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.15.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

 يتيمه

-0.70

IsMutable

-0.61

 חיצוניים

-0.58

 extérieures

-0.57

 généraux

-0.56

 mergeFrom

-0.56

 gruesa

-0.56

GEBURTSDATUM

-0.55

 géant

-0.54

 lumber

-0.54

POSITIVE LOGITS

 smaller

1.35

 small

1.31

 tiny

1.25

 Smaller

1.19

Small

1.17

Smaller

1.15

 SMALL

1.14

 smallest

1.11

 Small

1.11

small

1.10

Activations Density 0.522%

references to devices and their specifications, particularly in relation to size and functions

No Comments

No Known Activations