INDEX

Explanations

numbers, especially in a context related to contact information and ratings

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75

Prompts (Dashboard)

36,864 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

bootstrapcdn

-0.81

Geplaatst

-0.78

WithMany

-0.69

脚注の使い方

-0.69

Efq

-0.68

httphttps

-0.66

TagMode

-0.64

 الدولى

-0.64

Hentet

-0.63

Spoljašnje

-0.61

POSITIVE LOGITS

ThroughAttribute

0.49

AsUp

0.49

<bos>

0.48

 onPostExecute

0.46

InSection

0.44

 countertop

0.43

Fax

0.43

 Grüsse

0.41

 donate

0.40

Activations Density 0.128%

numbers, especially in a context related to contact information and ratings

No Comments

No Known Activations