INDEX

Explanations

references to various levels of order and classification in contexts such as academic or legal frameworks

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

sa

-0.53

else

-0.49

 final

-0.49

 dernière

-0.47

 otra

-0.45

sa

-0.45

 last

-0.45

 finally

-0.44

ét

-0.44

нивер

-0.43

POSITIVE LOGITS

 itſelf

1.05

 myſelf

1.04

Efq

1.03

AndEndTag

1.03

AddTagHelper

1.03

 disambiguazione

1.01

 виправивши

0.98

SourceChecksum

0.97

 فريبيس

0.95

Tikang

0.95

Activations Density 0.205%

references to various levels of order and classification in contexts such as academic or legal frameworks

No Comments

No Known Activations