INDEX

Explanations

phrases related to numerical increments and changes in programming contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

abestanden

-0.58

НИК

-0.55

protetor

-0.54

لز

-0.53

impresa

-0.53

GeneratedCode

-0.53

jména

-0.52

bkz

-0.52

 conseguenza

-0.52

 گوید

-0.52

POSITIVE LOGITS

 increment

0.67

 brows

0.64

increment

0.62

 Increment

0.61

WebMethod

0.58

IonicModule

0.54

 handels

0.53

 Departmental

0.53

Increment

0.52

ArgsConstructor

0.52

Activations Density 2.226%

phrases related to numerical increments and changes in programming contexts

No Comments

No Known Activations