INDEX

Explanations

references to favorite chapters or episodes within a discussion

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 23-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_23/width_16k/average_l0_120

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.23.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

CloseOperation

-0.74

UrlResolution

-0.69

IVEREF

-0.66

 faſt

-0.63

 Inſ

-0.63

ſelves

-0.62

 tartalomajánló

-0.62

ſelf

-0.62

 ſche

-0.60

 ſta

-0.60

POSITIVE LOGITS

 favorite

0.88

 favourite

0.74

 Favorite

0.72

 highlight

0.71

favorite

0.69

Favorite

0.66

 favorito

0.66

 favorites

0.63

 highlights

0.60

 FAVORITE

0.59

Activations Density 0.187%

references to favorite chapters or episodes within a discussion

No Comments

No Known Activations