INDEX

Explanations

terms related to efficiency and cognitive functions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

ers

-0.88

endphp

-0.75

mybatisplus

-0.68

ibatis

-0.64

onAttach

-0.63

 getopt

-0.62

Cass

-0.60

putExtra

-0.58

ERS

-0.58

tive

-0.57

POSITIVE LOGITS

ovi

0.71

 mellitus

0.68

Попис

0.63

OfYear

0.63

--;

0.63

 للمعارف

0.62

Estados

0.61

ingale

0.61

出版年

0.60

es

0.59

Activations Density 0.463%

terms related to efficiency and cognitive functions

No Comments

No Known Activations