INDEX

Explanations

phrases indicating questions and requests for confirmation or clarification regarding information

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

Followed by question mark or period

np_acts-logits-general · gemini-2.0-flash

questions and statements of uncertainty

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.24.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

 Commencez

-0.56

まずは

-0.52

Get

-0.52

hess

-0.50

ärna

-0.48

Get

-0.48

Find

-0.48

 smtplib

-0.47

 ideas

-0.47

ึกษา

-0.47

POSITIVE LOGITS

 Presumably

1.05

 IIRC

0.99

presumably

0.99

 presumably

0.99

 Interesting

0.85

 According

0.85

 Curious

0.85

Interesting

0.85

umably

0.85

According

0.84

Activations Density 0.343%

phrases indicating questions and requests for confirmation or clarification regarding information

Followed by question mark or period

questions and statements of uncertainty

No Comments

No Known Activations