INDEX

Explanations

instances of significant actions or changes relating to historical contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.4.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

 laude

-0.54

zent

-0.54

AKERS

-0.51

brata

-0.51

Viki

-0.51

psf

-0.51

paramref

-0.50

 OFDb

-0.50

ynb

-0.50

ativeness

-0.50

POSITIVE LOGITS

elemField

0.73

ViewFeatures

0.65

 hObject

0.61

IBOutlet

0.54

interpreter

0.54

 Réponses

0.51

elyn

0.51

 alleles

0.51

 Shand

0.51

äns

0.50

Activations Density 0.797%

instances of significant actions or changes relating to historical contexts

No Comments

No Known Activations