INDEX

Explanations

expressions indicating specific criteria or conditions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_13/width_16k/average_l0_132

Prompts (Dashboard)

24,576 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

 EconPapers

-0.91

 surla

-0.82

AddTagHelper

-0.81

 فريبيس

-0.80

AnchorStyles

-0.80

 indígen

-0.78

Personensuche

-0.77

ðsíða

-0.73

ValueStyle

-0.72

 resourceCulture

-0.70

POSITIVE LOGITS

 certain

0.96

 Certain

0.91

 particular

0.88

Certain

0.87

 specific

0.85

特定

0.83

certain

0.80

 tertentu

0.75

特定的

0.74

 particolari

0.72

Activations Density 0.511%

expressions indicating specific criteria or conditions

No Comments

No Known Activations