INDEX

Explanations

technical terms and components related to software, hardware, and programming

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

haped

-0.64

mej

-0.64

 arşivlendi

-0.57

eeded

-0.55

rawDesc

-0.53

BagLayout

-0.49

justed

-0.48

__["

-0.48

pecific

-0.47

ngthen

-0.46

POSITIVE LOGITS

Jereo

0.78

 zone

0.70

 houſe

0.68

 reticulum

0.64

 ſche

0.64

 tract

0.63

 corps

0.62

 center

0.61

 Jefus

0.61

 bloc

0.61

Activations Density 2.771%

technical terms and components related to software, hardware, and programming

No Comments

No Known Activations