INDEX

Explanations

phrases indicating user actions or requests

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

after punctuation marks

np_acts-logits-general · gemini-2.0-flash

apostrophes and periods in lists

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

 autorytatywna

-0.84

MessageTagHelper

-0.82

 myſelf

-0.77

surate

-0.76

rungsseite

-0.75

 doubtnut

-0.75

WaitGroup

-0.72

 Theſe

-0.68

 raiſ

-0.67

 poffible

-0.67

POSITIVE LOGITS

box

0.40

We

0.39

licht

0.38

box

0.37

The

0.36

GeneratedCode

0.35

чита

0.35

DeleteBehavior

0.35

Activations Density 0.034%

phrases indicating user actions or requests

after punctuation marks

apostrophes and periods in lists

No Comments

No Known Activations