INDEX

Explanations

phrases that indicate the perception or assessment of situations or people

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

 ModelExpression

-0.88

########.

-0.74

déric

-0.73

binant

-0.65

 ویکی‌پدیای

-0.62

 estekak

-0.61

 utafitiHapana

-0.61

QUENCE

-0.61

iyaki

-0.60

تقاوى

-0.60

POSITIVE LOGITS

 impression

0.75

 mentions

0.70

 Mentions

0.66

 impressions

0.65

 Impression

0.64

 impresion

0.64

Stocks

0.62

impression

0.61

 StatelessWidget

0.60

AF

0.60

Activations Density 0.148%

phrases that indicate the perception or assessment of situations or people

No Comments

No Known Activations