INDEX

Explanations

references to categories or classifications

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.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

 Himo

-0.69

Bibliograf

-0.61

 περι

-0.59

BagConstraints

-0.58

ToMany

-0.58

 hant

-0.57

DllImport

-0.55

FEW

-0.55

 Audiodateien

-0.54

ukunft

-0.53

POSITIVE LOGITS

 alguma

0.74

 algum

0.73

 somehow

0.72

 Something

0.68

Somehow

0.67

 valami

0.66

 Somehow

0.65

 alguna

0.65

 jakiś

0.65

 متعلقه

0.64

Activations Density 0.252%

references to categories or classifications

No Comments

No Known Activations

references to categories or classifications

No Comments

No Known Activations