INDEX

Explanations

statements related to announcements and sanctions

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

onViewCreated

-0.69

 Jefus

-0.67

 myſelf

-0.64

 createSlice

-0.62

ynchronously

-0.61

 purpoſe

-0.61

tvguidetime

-0.59

 Wiktionnaire

-0.58

 صوتيه

-0.58

uxxxx

-0.57

POSITIVE LOGITS

 restrictions

1.83

 restriction

1.71

ban

1.60

 bans

1.57

 Restrictions

1.53

 banning

1.47

 prohibition

1.45

 restrictive

1.44

 prohibitions

1.44

 Restriction

1.41

Activations Density 0.450%

statements related to announcements and sanctions

No Comments

No Known Activations