INDEX

Explanations

references to physical spaces and their arrangements or features

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_17/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.17.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

 للمعارف

-0.61

χύ

-0.54

utos

-0.52

styleable

-0.51

揄

-0.49

 snippetHide

-0.49

Rejo

-0.48

ItemCount

-0.47

 Channels

-0.46

 Himo

-0.46

POSITIVE LOGITS

 bedrooms

0.95

 upstairs

0.93

 bedroom

0.83

 downstairs

0.80

Bedrooms

0.80

Upstairs

0.72

 Bedrooms

0.71

 slept

0.70

 Bedroom

0.69

 dormitorios

0.69

Activations Density 0.021%

references to physical spaces and their arrangements or features

No Comments

No Known Activations