INDEX

Explanations

references to bedrooms in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.1.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

celess

-0.57

FEED

-0.52

 disponibilités

-0.52

 chargement

-0.51

 scissor

-0.50

 éclat

-0.50

 Speicher

-0.49

 FEED

-0.49

ugan

-0.49

Rüyada

-0.49

POSITIVE LOGITS

 bedroom

0.89

 Bedroom

0.84

ArgsConstructor

0.83

("")]

0.79

didSet

0.79

bedroom

0.79

Personendaten

0.78

Bedroom

0.77

 ModelExpression

0.75

httphttps

0.73

Activations Density 0.088%

references to bedrooms in various contexts

No Comments

No Known Activations