INDEX

Explanations

references to setting things aside or excluding specific details in a discussion

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

 Conſ

-0.64

 Houſe

-0.58

 Flin

-0.56

 orgasm

-0.56

 myſelf

-0.56

 positional

-0.56

retudo

-0.56

 itſelf

-0.55

Willkommen

-0.55

chle

-0.54

POSITIVE LOGITS

 &___

0.87

modelBuilder

0.73

tă

0.66

offsetof

0.66

MigrationBuilder

0.65

Diwedd

0.63

dì

0.62

cres

0.60

qrstuvwxyz

0.59

rawDesc

0.59

Activations Density 0.112%

references to setting things aside or excluding specific details in a discussion

No Comments

No Known Activations