INDEX

Explanations

terms related to dimensional models and guides in a technical context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_6/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.6.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

Ча

-0.54

Detalhes

-0.52

Mount

-0.49

 Detal

-0.48

Quaternion

-0.47

Setter

-0.46

likopter

-0.46

 ча

-0.46

rimp

-0.45

 Weather

-0.45

POSITIVE LOGITS

 length

0.80

ParallelGroup

0.77

ChildScrollView

0.72

 corridor

0.72

 Streifen

0.69

 lengths

0.68

 strip

0.68

length

0.68

 liné

0.67

 strips

0.66

Activations Density 0.869%

terms related to dimensional models and guides in a technical context

No Comments

No Known Activations