INDEX

Explanations

references to former individuals in various roles or positions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

SBATCH

-0.71

 intptr

-0.68

 Shoulders

-0.65

 auguri

-0.62

anniversaire

-0.59

 سكانية

-0.58

 AssemblyVersion

-0.58

XmlType

-0.55

currently

-0.55

 prochaines

-0.54

POSITIVE LOGITS

 employees

0.71

 employee

0.67

 president

0.65

ⓧ

0.64

NFL

0.60

 Yugoslavia

0.59

 glories

0.59

 longtime

0.59

 colleagues

0.59

 mayor

0.58

Activations Density 0.100%

references to former individuals in various roles or positions

No Comments

No Known Activations