INDEX

Explanations

references to prior legal cases or precedents

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_9/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.9.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

 Hake

-0.90

DMT

-0.88

 Landau

-0.87

thansa

-0.86

ÍTICA

-0.86

 Reichen

-0.85

LabelTagHelper

-0.84

artney

-0.83

 meste

-0.82

lectricité

-0.82

POSITIVE LOGITS

or

1.25

ator

1.10

stor

1.03

ors

1.02

vor

0.98

OR

0.98

por

0.96

otor

0.96

itor

0.92

lor

0.92

Activations Density 0.257%

references to prior legal cases or precedents

No Comments

No Known Activations