INDEX

Explanations

terms related to sending messages or data in a network communication context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.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

 disambiguazione

-0.70

 Trotter

-0.64

ORIENTATION

-0.62

 wier

-0.62

Cyfeiriadau

-0.61

Jereo

-0.60

Lycka

-0.59

('.');

-0.58

offices

-0.58

Epit

-0.57

POSITIVE LOGITS

send

1.70

SEND

1.43

Send

1.41

 Send

1.32

 SEND

1.30

 send

1.08

recv

1.04

 发送

0.93

//

0.85

 recv

0.84

Activations Density 0.072%

terms related to sending messages or data in a network communication context

No Comments

No Known Activations