INDEX

Explanations

phrases and references to the term "down" and its variations

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

Viki

-1.04

 Magi

-0.96

érêt

-0.82

PhysRev

-0.80

ⅰ

-0.80

ungguhnya

-0.79

ließlich

-0.78

 Mercier

-0.78

Ivoire

-0.77

KindOfClass

-0.75

POSITIVE LOGITS

 down

1.79

 Down

1.73

Down

1.69

 DOWN

1.64

down

1.55

DOWN

1.49

downs

1.40

Downs

1.33

 downs

1.27

 Downs

1.22

Activations Density 0.076%

phrases and references to the term "down" and its variations

No Comments

No Known Activations