INDEX

Explanations

legal terminology and references to court proceedings

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.19.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

LookAnd

-0.60

protoimpl

-0.55

intios

-0.51

ništvo

-0.50

annica

-0.50

 kasarigan

-0.49

Становништво

-0.48

 CreateTagHelper

-0.47

outé

-0.46

itself

-0.46

POSITIVE LOGITS

 whose

1.23

whose

1.22

 whoſe

1.07

 seus

1.04

 whofe

1.03

their

1.01

 Whose

1.00

seu

0.97

 their

0.97

Their

0.96

Activations Density 0.557%

legal terminology and references to court proceedings

No Comments

No Known Activations