INDEX

Explanations

references to legacy, memory, and the honoring of individuals

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.17.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

 oprot

-0.76

出版年

-0.70

GEBURTSDATUM

-0.63

MLLoader

-0.56

urgis

-0.55

PreExecute

-0.54

GraphicsUnit

-0.53

 оригіналу

-0.53

ulkner

-0.53

jenost

-0.53

POSITIVE LOGITS

 legacy

1.22

legacy

0.95

 legacies

0.86

 legado

0.83

 memory

0.83

 Legacy

0.80

Legacy

0.80

 memories

0.77

 continue

0.76

 CONTIN

0.69

Activations Density 0.163%

references to legacy, memory, and the honoring of individuals

No Comments

No Known Activations