INDEX

Explanations

references to something significant or outstanding, often marked by the term "great."

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

脚注の使い方

-0.88

Referències

-0.77

 disambiguazione

-0.76

FileDescriptor

-0.75

Hochspringen

-0.74

URLException

-0.72

ReusableCell

-0.72

 Juno

-0.72

حوال

-0.71

 AssemblyTitle

-0.70

POSITIVE LOGITS

great

1.98

GREAT

1.91

 Great

1.88

 great

1.85

Great

1.84

 GREAT

1.81

 greatness

1.34

 greatest

1.28

TheGreat

1.22

greatest

1.18

Activations Density 0.080%

references to something significant or outstanding, often marked by the term "great."

No Comments

No Known Activations