INDEX

Explanations

text related to user account management and verification processes

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

Text in languages other than English

np_acts-logits-general · gemini-2.0-flash

vaizdą ar

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-16k

Configuration

google/gemma-scope-9b-it-res/layer_31/width_16k/average_l0_76

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 EconPapers

-0.80

verwijspagina

-0.78

 تضيفلها

-0.74

Tikang

-0.71

ThroughAttribute

-0.71

 pinulongan

-0.70

dafx

-0.68

AISSEE

-0.68

 linkovi

-0.68

 Infórmanos

-0.66

POSITIVE LOGITS

pot

0.38

ba

0.35

 Bailly

0.32

 erythrocytes

0.30

apo

0.30

 australian

0.30

 pres

0.30

na

0.29

 solvent

0.29

 dispersion

0.29

Activations Density 0.024%

text related to user account management and verification processes

Text in languages other than English

vaizdą ar

No Comments

No Known Activations