INDEX

Explanations

requests and actions related to deleting or modifying information

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

Follows "of" or "delete"

np_acts-logits-general · gemini-2.0-flash

of these

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ANTLR

-0.52

htaccess

-0.52

ITERIA

-0.51

 laude

-0.51

zkopf

-0.50

+:+

-0.49

ípio

-0.49

 multer

-0.49

postmedia

-0.49

POSITIVE LOGITS

 Roskov

0.72

Personendaten

0.68

 solcher

0.58

 ſeveral

0.58

RegistryLite

0.57

 solches

0.57

 betweenstory

0.56

 ejus

0.56

 habet

0.56

 iſt

0.56

Activations Density 0.601%

requests and actions related to deleting or modifying information

Follows "of" or "delete"

of these

No Comments

No Known Activations