INDEX

Explanations

terminology related to electrical circuits and components

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

Negative Logits

 memorial

-0.55

[]:

-0.54

writeField

-0.49

 ffilm

-0.47

agge

-0.46

 Memorial

-0.46

 MEMORIAL

-0.44

prehension

-0.42

磨

-0.42

omyces

-0.41

POSITIVE LOGITS

 power

0.74

detectChanges

0.70

GEBURTSDATUM

0.68

contentLoaded

0.68

 converter

0.67

PWM

0.67

mybatisplus

0.67

GBT

0.65

queryInterface

0.65

الدراسه

0.64

Activations Density 0.234%

terminology related to electrical circuits and components

No Known Activations