INDEX

Explanations

references to procedures or methodologies

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.1.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

addContainerGap

-0.67

IContainer

-0.57

 tool

-0.56

pablo

-0.55

pa

-0.55

 mass

-0.55

 residency

-0.54

 chain

-0.54

arana

-0.54

FL

-0.53

POSITIVE LOGITS

 according

4.18

according

3.80

According

3.24

 According

3.24

 selon

2.81

 según

2.73

 ACCORD

2.71

 volgens

2.62

 accordance

2.49

 enligt

2.41

Activations Density 0.099%

references to procedures or methodologies

No Comments

No Known Activations