INDEX

Explanations

references to legal terminology and processes

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

 autorytatywna

-0.52

DataAnnotations

-0.51

šn

-0.45

…

-0.45

PageContext

-0.45

fseek

-0.44

㎡

-0.43

 Kamu

-0.42

ushima

-0.41

{"

-0.41

POSITIVE LOGITS

 thereof

0.93

 such

0.93

 these

0.91

 latter

0.89

 SUCH

0.89

そのような

0.89

そちら

0.87

 tersebut

0.87

 daarvan

0.85

Such

0.84

Activations Density 0.981%

references to legal terminology and processes

No Comments

No Known Activations