INDEX

Explanations

references to formal inquiries and reviews related to accountability

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

 ostavi

-0.69

awtextra

-0.67

AndEndTag

-0.65

óg

-0.64

 Bolivar

-0.63

Obrázky

-0.62

 Италијани

-0.61

bán

-0.59

valently

-0.58

PreferredItem

-0.58

POSITIVE LOGITS

 report

0.65

 committee

0.65

 chaired

0.64

 investigating

0.62

 examining

0.59

 inquiry

0.56

 tasked

0.55

 investigation

0.55

QUIRY

0.55

CWE

0.54

Activations Density 0.310%

references to formal inquiries and reviews related to accountability

No Comments

No Known Activations