INDEX

Explanations

details about spatial layouts and features of living spaces

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 protoimpl

-0.53

dyna

-0.46

]")]

-0.45

Sc

-0.44

 Shetterly

-0.44

dyn

-0.44

DY

-0.43

dy

-0.43

 gainera

-0.43

gania

-0.41

POSITIVE LOGITS

webElementXpaths

0.75

matchCondition

0.64

 writeTo

0.61

 Ensuite

0.61

 Closet

0.61

printStackTrace

0.61

Ensuite

0.60

قایناقلار

0.60

onAttach

0.60

WriteAttribute

0.60

Activations Density 0.061%

details about spatial layouts and features of living spaces

No Comments

No Known Activations