INDEX

Explanations

programming-related syntax and structures

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/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.13.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

 autorytatywna

-0.67

AutoScaleMode

-0.64

 Réponses

-0.53

 Audiodateien

-0.53

 상세

-0.51

 perd

-0.51

ThroughAttribute

-0.50

Skocz

-0.49

 dure

-0.49

POSITIVE LOGITS

 Chriftian

0.68

 Majefty

0.62

 Chrif

0.58

لكتر

0.57

 isolato

0.57

 neighbours

0.55

 Adagio

0.55

 imprimé

0.55

Efq

0.54

 inalámbrico

0.53

Activations Density 0.093%

programming-related syntax and structures

No Comments

No Known Activations