INDEX

Explanations

references to specific cases or conditions in a scientific or technical context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

はじめに

-0.35

badah

-0.32

公司

-0.30

 Hül

-0.30

contentLoaded

-0.30

Pipeline

-0.29

StylePriority

-0.29

BaseEntity

-0.29

 Parr

-0.29

 bertanggung

-0.29

POSITIVE LOGITS

 cazul

0.72

 cases

0.59

antMatchers

0.58

 caso

0.58

AndEndTag

0.55

 majority

0.55

 frigid

0.55

 NSCoder

0.54

 certain

0.52

 CASO

0.52

Activations Density 0.797%

references to specific cases or conditions in a scientific or technical context

No Comments

No Known Activations