INDEX

Explanations

references to destructive behaviors and their consequences

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.15.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

-0.44

gano

-0.43

lad

-0.39

зан

-0.38

iong

-0.37

核

-0.36

άρ

-0.36

kern

-0.36

Overview

-0.36

تص

-0.35

POSITIVE LOGITS

GOTREF

0.99

 AssemblyCulture

0.95

今度は

0.93

GEBURTSDATUM

0.89

 виправивши

0.89

now

0.86

 незавершена

0.84

 EconPapers

0.83

 ahora

0.82

 gyhoeddwyd

0.82

Activations Density 0.462%

references to destructive behaviors and their consequences

No Comments

No Known Activations

references to destructive behaviors and their consequences

No Comments

No Known Activations