INDEX

Explanations

elements related to confirmation or approval processes

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

official notices and announcements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.31.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

OGND

-0.80

 Infórmanos

-0.68

IsContent

-0.65

GEBURTSDATUM

-0.64

setVerticalGroup

-0.63

RectangleBorder

-0.63

 Autorizaciones

-0.63

 NSCoder

-0.59

 CreateTagHelper

-0.58

 autorytatywna

-0.57

POSITIVE LOGITS

 notice

0.57

 memo

0.54

 letter

0.49

 memorandum

0.45

 flyer

0.42

 announcement

0.42

 Notice

0.42

 bulletin

0.40

 yhte

0.40

 notification

0.40

Activations Density 0.017%

elements related to confirmation or approval processes

official notices and announcements

No Comments

No Known Activations