INDEX

Explanations

descriptions of people and their physical characteristics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

epam

-0.49

とおり

-0.47

通り

-0.44

OGEN

-0.44

 publique

-0.44

lless

-0.43

 lettre

-0.43

 Cuerpo

-0.42

Waga

-0.42

 kém

-0.42

POSITIVE LOGITS

bewerken

0.71

ftagPool

0.66

 AssemblyProduct

0.65

 ostavi

0.65

 nahilalakip

0.62

 похоже

0.62

 seemed

0.59

bootstrapcdn

0.59

SaveChangesAsync

0.59

msgTypes

0.59

Activations Density 0.249%

descriptions of people and their physical characteristics

No Comments

No Known Activations