INDEX

Explanations

references to opening, accessibility, or inclusivity

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 تضيفلها

-0.96

 onPostExecute

-0.96

 consultato

-0.70

TagMode

-0.68

Personensuche

-0.68

DllImport

-0.67

 ExecuteAsync

-0.66

TimerTask

-0.64

 doInBackground

-0.63

تقاوى

-0.63

POSITIVE LOGITS

 open

1.46

 openness

1.31

 Open

1.29

 OPEN

1.26

Open

1.23

OPEN

1.18

open

1.17

 opened

1.11

 opens

1.07

开放

1.07

Activations Density 0.216%

references to opening, accessibility, or inclusivity

No Comments

No Known Activations