INDEX

Explanations

references to debugging activities and commands

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

EndGlobalSection

-0.95

новниш

-0.68

Spoljašnje

-0.55

Abitanti

-0.52

gouv

-0.51

Ārējās

-0.50

 péld

-0.48

نجليزية

-0.47

InputTagHelper

-0.46

Geplaatst

-0.46

POSITIVE LOGITS

GroupLayout

1.26

PREFERRED

0.82

IsContent

0.81

tvguidetime

0.65

hdashline

0.62

MENAFN

0.59

Rhestr

0.59

LayoutStyle

0.58

PUS

0.58

 JAXBElement

0.58

Activations Density 0.038%

references to debugging activities and commands

No Comments

No Known Activations