INDEX

Explanations

references to legal terms and proceedings

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

+#+#

-1.05

Obrázky

-0.81

 poffible

-0.75

 auffi

-0.73

 purpoſe

-0.70

 iſt

-0.69

 pleaſure

-0.69

findpost

-0.69

 initComponents

-0.68

 désolés

-0.67

POSITIVE LOGITS



0.51

ﷺ

0.47

det

0.43

Története

0.43

 információk

0.42

Bo

0.41

 Status

0.41

Sp

0.41

 status

0.40

$\

0.40

Activations Density 0.842%

references to legal terms and proceedings

No Comments

No Known Activations