INDEX

Explanations

terms related to adjustment or modification

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

adjust

np_max-act-logits · gpt-4o-mini Triggered by @johnny

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

 disambiguazione

-0.91

LLocation

-0.83

onViewCreated

-0.83

aarrggbb

-0.80

RegistryLite

-0.73

ClientSize

-0.73

 doInBackground

-0.71

makeText

-0.71

 MaterialApp

-0.70

:✨

-0.70

POSITIVE LOGITS

 adjusted

0.97

 adjust

0.94

 adapted

0.85

adjusted

0.82

archive

0.76

 Adjusted

0.75

 archive

0.69

adjust

0.69

 adapt

0.66

Adjusted

0.65

Activations Density 0.147%

terms related to adjustment or modification

adjust

No Comments

No Known Activations