INDEX

Explanations

references to prime numbers or PM (presumably related to certain contexts like project management or personnel management)

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

DoubleQuotes

-0.64

期刊论文

-0.64

 pinulongan

-0.58

INARY

-0.53

 Hooper

-0.51

"…

-0.49

 пой

-0.49

Corresponding

-0.48

yim

-0.48

hicles

-0.48

POSITIVE LOGITS

RectangleBorder

0.86

 prime

0.79

PM

0.77

 للمعارف

0.76

Prime

0.73

Posted

0.70

PRIME

0.69

 PRIME

0.69

 Prime

0.68

pm

0.67

Activations Density 0.160%

references to prime numbers or PM (presumably related to certain contexts like project management or personnel management)

No Comments

No Known Activations