INDEX

Explanations

code-related elements and syntax

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.14.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

IsMutable

-0.81

parsedMessage

-0.72

UnusedPrivate

-0.70

 defaultstate

-0.69

 saites

-0.69

HasForeignKey

-0.68

 дописавши

-0.67

GraphicsUnit

-0.67

IsContent

-0.66

 Theſe

-0.65

POSITIVE LOGITS

Autoritní

0.54

+#+

0.53

subsubsection

0.52

JAKARTA

0.52

aliyun

0.47

 VizieR

0.46

MADRID

0.46

 šte

0.45

Dichloropropene

0.45

 consenso

0.45

Activations Density 0.824%

code-related elements and syntax

No Comments

No Known Activations