INDEX

Explanations

references to legal cases or judicial terms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.1.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

providedIn

-0.59

ರು

-0.53

gameserver

-0.52

Beau

-0.49

Tages

-0.49

ละ

-0.49

ьев

-0.47

fub

-0.47

ichter

-0.46

@#

-0.46

POSITIVE LOGITS

ell

0.85

 témoin

0.79

ELL

0.73

 moons

0.73

 Testimony

0.72

 endwhile

0.72

elling

0.71

 onAnimation

0.71

 mourn

0.69

 survivor

0.69

Activations Density 2.363%

references to legal cases or judicial terms

No Comments

No Known Activations