INDEX

Explanations

references to the ground or ground-related terms

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

ground and things that follow

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.9.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

 AssemblyVersion

-0.41

ExtendWith

-0.41

:✨

-0.40

TestId

-0.39

 ISNI

-0.39

Sip

-0.38

SIP

-0.38

 ensure

-0.38

Cosmic

-0.38

ensure

-0.36

POSITIVE LOGITS

ground

2.34

grounds

2.25

Ground

2.03

GROUND

1.98

 Ground

1.89

 GROUND

1.79

 ground

1.78

 Grounds

1.59

 grounds

1.41

 grounding

1.07

Activations Density 0.003%

references to the ground or ground-related terms

ground and things that follow

No Comments

No Known Activations