INDEX

Explanations

legal arguments and judicial reasoning

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 насељу

-1.04

 Roskov

-1.00

ValueStyle

-0.99

SharedDtor

-0.96

ViewFeatures

-0.92

DeleteBehavior

-0.91

 nahilalakip

-0.89

Portale

-0.87

parsedMessage

-0.87

 дописавши

-0.85

POSITIVE LOGITS

gal

0.47

oche

0.46

…

0.46

0.44

 (…)

0.43

…

0.43

...

0.43

rom

0.41

he

0.41

ent

0.41

Activations Density 0.675%

legal arguments and judicial reasoning

No Comments

No Known Activations