INDEX

Explanations

references to personal experiences and demographics related to living in the US

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_6/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.6.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

 themſelves

-0.87

GOTREF

-0.86

 ویکی‌پدیای

-0.83

 itſelf

-0.78

campista

-0.78

 pleaſure

-0.76

 ſtate

-0.76

ſelf

-0.76

 myſelf

-0.75

Efq

-0.74

POSITIVE LOGITS

0.55

0.47

Be

0.43

 kind

0.41

 generally

0.40

 makes

0.40

 living

0.39

…

0.39

 consultato

0.39

Activations Density 0.288%

references to personal experiences and demographics related to living in the US

No Comments

No Known Activations