INDEX

Explanations

references to legal terminology and court rulings

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

 <=",

-0.94

 '\\;'

-0.91

protoimpl

-0.88

 AssemblyCulture

-0.86

expandindo

-0.83

principalTable

-0.83

 GenerationType

-0.83

rhosis

-0.83

 AssemblyCompany

-0.83

 Administrativna

-0.82

POSITIVE LOGITS

 régionales

0.59

 étrangères

0.55

 Unies

0.53

 naturelles

0.52

 supérieures

0.50

 européennes

0.49

↵↵

0.49

 humaines

0.47

 sanitaires

0.47

kus

0.47

Activations Density 0.145%

references to legal terminology and court rulings

No Comments

No Known Activations