INDEX

Explanations

references to variable types or definitions 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 @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

 kasarigan

-0.77

gonic

-0.57

 sạn

-0.54

gaon

-0.53

 địch

-0.53

TRIBUT

-0.53

VersionUID

-0.52

IRQn

-0.50

urator

-0.49

 getToken

-0.49

POSITIVE LOGITS

<&

0.82

 aéri

0.78

abestanden

0.71

="@+

0.69

 almendras

0.68

 spese

0.67

aarrggbb

0.67

 vectorielles

0.65

 Adagio

0.63

0.62

Activations Density 0.034%

references to variable types or definitions in programming contexts

No Comments

No Known Activations