INDEX

Explanations

references to personal identity and self-discovery

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_10/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.10.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

 оригіналу

-0.48

 transfert

-0.48

 nakalista

-0.48

 صوتيه

-0.47

kingen

-0.46

遥

-0.45

 compro

-0.45

勘

-0.45

rob

-0.44

Specifically

-0.44

POSITIVE LOGITS

RectangleBorder

0.87

ribadian

0.79

LLocation

0.76

 selves

0.75

 identity

0.72

 мәкал

0.70

EDEFAULT

0.69

ButterKnife

0.68

PageFactory

0.68

ikkert

0.67

Activations Density 0.267%

references to personal identity and self-discovery

No Comments

No Known Activations