INDEX

Explanations

phrases related to legal terms and mathematical sequences

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.11.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

MENAFN

-0.69

Cubit

-0.62

 veuillez

-0.59

 Jefus

-0.57

 Theorems

-0.56

 Reſ

-0.56

 Euclidean

-0.56

 zelve

-0.55

ները

-0.54

 itſelf

-0.54

POSITIVE LOGITS

 that

0.59

dafx

0.55

 Chwiliwch

0.53

şiv

0.52

 referenties

0.49

verwijspagina

0.49

substack

0.48

}));

0.48

ResumeLayout

0.46

getchar

0.46

Activations Density 0.807%

phrases related to legal terms and mathematical sequences

No Comments

No Known Activations