INDEX

Explanations

phrases and expressions that pose questions

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.2.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

lepiej

-0.70

بوابة

-0.68

 poitrine

-0.66

 grève

-0.66

 gloire

-0.62

BorderLayout

-0.62

Polecam

-0.62

 poignée

-0.62

Metode

-0.61

 versioni

-0.61

POSITIVE LOGITS

 question

4.01

 questions

3.48

 Question

3.44

question

3.38

Question

3.12

 QUESTION

3.08

 Questions

2.96

questions

2.90

Questions

2.81

 Frage

2.66

Activations Density 0.073%

phrases and expressions that pose questions

No Comments

No Known Activations