INDEX

Explanations

references to parts or episodes in a structured format

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-9b-pt-res/layer_9/width_16k/average_l0_100

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.9.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

-0.52

 وتسجيلات

-0.47

ForValue

-0.45

 cappello

-0.44

ंदीखरीदारी

-0.43

RenderAtEndOf

-0.43

Cyfeiriadau

-0.43

Bibliograf

-0.42

 factory

-0.42

 Riproduzione

-0.41

POSITIVE LOGITS

Part

0.80

 Part

0.77

 Parts

0.64

 Parte

0.62

Parte

0.61

Часть

0.60

Parts

0.59

PART

0.59

part

0.59

 PART

0.57

Activations Density 0.433%

references to parts or episodes in a structured format

No Comments

No Known Activations