INDEX

Explanations

formatted code snippets, particularly those involving parameters and operators

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_6/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.6.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

aarrggbb

-0.68

 חיצוניים

-0.68

 dataSnapshot

-0.67

onViewCreated

-0.66

 kommit

-0.64

########.

-0.62

hyrchwyd

-0.61

[]>(

-0.60

principalTable

-0.57

 épis

-0.56

POSITIVE LOGITS

 myſelf

0.82

 Majefty

0.78

 Jefus

0.76

 Monfieur

0.75

tvguidetime

0.71

ſelf

0.70

Efq

0.68

 تضيفلها

0.67

 Houſe

0.66

neſs

0.65

Activations Density 0.406%

formatted code snippets, particularly those involving parameters and operators

No Comments

No Known Activations