INDEX

Explanations

terms and phrases related to depth and profoundness 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 @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

 propOrder

-0.95

antMatchers

-0.94

RegistryLite

-0.90

AccessorTable

-0.82

 Montrose

-0.81

urlpatterns

-0.80

DebuggerNonUser

-0.78

ritation

-0.78

 dévelo

-0.77

 ModelRenderer

-0.77

POSITIVE LOGITS

 DEEP

1.65

 deep

1.62

 Deep

1.57

Deep

1.43

deep

1.40

 depths

1.40

 depth

1.39

DEEP

1.38

 deeply

1.30

 Depth

1.30

Activations Density 0.057%

terms and phrases related to depth and profoundness in various contexts

No Comments

No Known Activations