INDEX

Explanations

references to periods of time, particularly involving days and hours

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

 /\.(

-0.88

izeit

-0.67

rendon

-0.63

 HasFactory

-0.62

랬

-0.60

 torchvision

-0.60

-0.59

Kaw

-0.59

Welche

-0.59

các

-0.58

POSITIVE LOGITS

 months

0.90

 weeks

0.86

vernight

0.77

 Monate

0.74

 minutes

0.72

 maanden

0.72

weeks

0.70

months

0.69

 Monaten

0.69

 seconds

0.68

Activations Density 0.207%

references to periods of time, particularly involving days and hours

No Comments

No Known Activations