INDEX

Explanations

relationships between variables in statistical models

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.11.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

INGE

-0.44

weise

-0.40

ani

-0.40

 derr

-0.40

 Vorsch

-0.39

 Smart

-0.39

er

-0.39

fruta

-0.38

re

-0.38

orchid

-0.38

POSITIVE LOGITS

SourceChecksum

1.01

+#+#

0.97

ArrowToggle

0.94

LookAnd

0.91

 autorytatywna

0.88

 HasFactory

0.85

mybatisplus

0.82

Portale

0.79

CloseOperation

0.78

RTDA

0.78

Activations Density 1.328%

relationships between variables in statistical models

No Comments

No Known Activations