INDEX

Explanations

updates and revisions in a document

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

хьтан

-0.60

Personendaten

-0.59

 Allociné

-0.58

dersfield

-0.56

hasMany

-0.55

ViewChild

-0.54

imageshack

-0.53

virt

-0.53

 tkinter

-0.53

 pytest

-0.52

POSITIVE LOGITS

 updated

1.92

 updating

1.73

 updates

1.70

 Updating

1.65

 Updated

1.64

updated

1.59

 update

1.59

 Updates

1.58

Updated

1.50

 更新

1.47

Activations Density 0.113%

updates and revisions in a document

No Comments

No Known Activations