INDEX

Explanations

different types of list or array structures

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

 Aires

-0.55

oyn

-0.54

 OnEnable

-0.53

 Cubans

-0.53

 tremb

-0.53

 pensée

-0.53

 Lausanne

-0.53

 sobretudo

-0.52

UPM

-0.52

Napoli

-0.52

POSITIVE LOGITS

 leadership

0.83

 returning

0.77

 toilet

0.74

 heading

0.72

sho

0.71

ensement

0.70

archiviato

0.69

 发表于

0.68

LLocation

0.66

 Heading

0.65

Activations Density 0.053%

different types of list or array structures

No Comments

No Known Activations