INDEX

Explanations

phrases indicating personal bias or subjective reflections

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 للمعارف

-0.66

-0.63

PMailer

-0.60

++){

-0.59

}{*}{}

-0.58

Autoritní

-0.57

 Audiodateien

-0.57

 snippetHide

-0.57

devamını

-0.56

 виправивши

-0.56

POSITIVE LOGITS

luck

0.56

 precaution

0.55

 effort

0.55

 shutil

0.54

stopPropagation

0.54

 attempt

0.52

 mắn

0.52

celes

0.52

rungsseite

0.52

 luck

0.51

Activations Density 0.543%

phrases indicating personal bias or subjective reflections

No Comments

No Known Activations