INDEX

Explanations

mentions of the Python programming language

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

WebServlet

-0.56

 GenerationType

-0.55

 plan

-0.54

็จ

-0.54

Scho

-0.51

fo

-0.51

िखित

-0.48

قي

-0.48

 blows

-0.47

达

-0.47

POSITIVE LOGITS

 myſelf

0.72

tamanya

0.70

tichetta

0.69

GEBURTSDATUM

0.68

agisse

0.68

 Abonnez

0.68

 reviewer

0.67

sizeCache

0.66

 ostavi

0.65

 Anſ

0.64

Activations Density 0.161%

mentions of the Python programming language

No Comments

No Known Activations