INDEX

Explanations

legal terminology and references within documents

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

 للمعارف

-0.75

featureID

-0.65

createCanvas

-0.64

 وتسجيلات

-0.62

 disponibilités

-0.62

UserScript

-0.57

FACTS

-0.54

thenReturn

-0.54

Ingredienti

-0.53

 consultato

-0.53

POSITIVE LOGITS

UrlResolution

0.65

Datuak

0.59

 plagioclase

0.58

الدراسه

0.57

 thereto

0.57

awtextra

0.54

idoscope

0.54

 myſelf

0.53

 Boek

0.53

insic

0.52

Activations Density 0.143%

legal terminology and references within documents

No Comments

No Known Activations