INDEX

Explanations

references to government actions or statements regarding controversial issues

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 35-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_35/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.35.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

 pensó

-0.30

:]:

-0.30

 świad

-0.29

 enamor

-0.29

 cận

-0.28

 tinker

-0.28

 cumplido

-0.28

 czasem

-0.28

zerű

-0.28

 tinkering

-0.28

POSITIVE LOGITS

 condemn

1.43

 Condem

1.36

 condemned

1.34

 condemning

1.34

 condemnation

1.30

 condemns

1.27

 condem

1.18

 condam

1.06

 denounce

1.05

 denounced

1.05

Activations Density 0.364%

references to government actions or statements regarding controversial issues

No Comments

No Known Activations