INDEX

Explanations

mentions of hierarchical structures and classifications

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 8-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_8/width_16k/average_l0_99

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.8.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

ConstraintMaker

-0.59

ImageContext

-0.52

twimg

-0.52

GOTREF

-0.52

ergies

-0.52

emplares

-0.51

 spalle

-0.49

dcmtk

-0.49

rosin

-0.48

قایناق‌لار

-0.48

POSITIVE LOGITS

 levels

1.04

 level

0.97

Levels

0.95

levels

0.91

 Levels

0.89

 tiers

0.88

 LEVELS

0.86

Level

0.85

 nivel

0.83

 stages

0.83

Activations Density 0.523%

mentions of hierarchical structures and classifications

No Comments

No Known Activations