INDEX

Explanations

various forms and contexts of the word "deep" and related phrases indicative of depth and substantiality

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

antMatchers

-0.84

ritation

-0.74

 Montrose

-0.73

RegistryLite

-0.73

 Shetty

-0.71

flashdata

-0.71

kháu

-0.71

urlpatterns

-0.70

 ModelRenderer

-0.70

OGND

-0.69

POSITIVE LOGITS

 DEEP

1.71

 deep

1.70

 Deep

1.57

 depths

1.49

Deep

1.48

 depth

1.47

deep

1.45

DEEP

1.45

 deeply

1.38

 Depth

1.38

Activations Density 0.106%

various forms and contexts of the word "deep" and related phrases indicative of depth and substantiality

No Comments

No Known Activations