INDEX

Explanations

expressions related to ethical concerns and decision-making

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 22-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_22/width_16k/average_l0_123

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

 للمعارف

-0.52

 étoient

-0.44

 olet

-0.43

 pegatina

-0.43

 autorytatywna

-0.43

 Sünde

-0.42

 desemple

-0.42

 sonriendo

-0.42

 hierro

-0.42

 pamięci

-0.42

POSITIVE LOGITS

 scheduled

0.49

 reschedule

0.48

 postponed

0.46

 postponement

0.45

 delay

0.45

 postpone

0.44

 postpon

0.44

 decision

0.44

 Decision

0.43

 indefinite

0.42

Activations Density 0.154%

expressions related to ethical concerns and decision-making

No Known Activations