INDEX

Explanations

references to clients in a programming context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.19.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

verwijspagina

-0.86

 AssemblyTitle

-0.76

NameInMap

-0.73

saraba

-0.71

 ویکی‌پدی

-0.67

MENAFN

-0.66

ⓘ

-0.66

testify

-0.66

Autoritní

-0.65

-0.62

POSITIVE LOGITS

 getClient

1.22

 clients

1.19

 Clients

1.14

clients

1.08

 CLIENT

1.06

Clients

1.05

 client

0.96

 Client

0.95

getClient

0.92

CLIENT

0.89

Activations Density 0.048%

references to clients in a programming context

No Comments

No Known Activations