INDEX

Explanations

expressions indicating widespread distribution or presence

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

出版年

-0.84

icoot

-0.77

berra

-0.68

rahat

-0.64

DNEY

-0.60

batross

-0.58

BagConstraints

-0.58

gants

-0.57

 נוסף

-0.56

ottes

-0.55

POSITIVE LOGITS

 partout

0.91

 everywhere

0.89

Everywhere

0.79

 Everywhere

0.76

 ovunque

0.75

 désolés

0.75

 everybody

0.74

everywhere

0.73

///</

0.70

 onBind

0.70

Activations Density 0.038%

expressions indicating widespread distribution or presence

No Comments

No Known Activations