INDEX

Explanations

geographic names and references

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

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

 Shand

-0.84

 odkazy

-0.75

BagConstraints

-0.74

JsonProperty

-0.73

crollView

-0.72

 Nuss

-0.71

IntegrationTest

-0.70

AutoScaleMode

-0.70

 Sand

-0.67

 UITableViewCell

-0.67

POSITIVE LOGITS

 Assam

0.98

wahati

0.89

 Guwahati

0.78

NSW

0.75

 Iraq

0.72

Iraq

0.71

 Iraqi

0.71

NSW

0.70

Connecticut

0.69

 Connecticut

0.68

Activations Density 1.105%

geographic names and references

No Comments

No Known Activations