INDEX

Explanations

questions and prompts for elaboration or discussion

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-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

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

 estekak

-0.98

 MainAxisSize

-0.92

UrlResolution

-0.92

Autoritní

-0.88

 geſch

-0.86

bootstrapcdn

-0.86

 الرياضيه

-0.85

 فريبيس

-0.85

expandindo

-0.84

 ſei

-0.83

POSITIVE LOGITS

Is

0.29

What

0.28

0.27

Can

0.27

Has

0.27

Would

0.27

 söyle

0.26

Activations Density 0.005%

questions and prompts for elaboration or discussion

No Comments

No Known Activations