INDEX

Explanations

phrases that express affirmation or correctness

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.10.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

“

-0.50

-0.45

”

-0.44

 جهت

-0.43

 post

-0.43

ække

-0.41

-0.40

 milieux

-0.40

 demo

-0.40

POSITIVE LOGITS

AccessorTable

0.89

 Signalez

0.87

Personensuche

0.86

 Paglinawan

0.86

تقاوى

0.86

 المعيارى

0.85

GEBURTSDATUM

0.84

principalColumn

0.80

 kasarigan

0.79

脚注の使い方

0.78

Activations Density 0.196%

phrases that express affirmation or correctness

No Comments

No Known Activations