INDEX

Explanations

specific numerical values and their relationships within a structured context

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

Non-English or code-related text

np_acts-logits-general · gemini-2.0-flash

response fausse

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

gunt

-0.82

 Arund

-0.79

baj

-0.78

arent

-0.78

ofollow

-0.77

 Khat

-0.76

ammen

-0.75

 autorytatywna

-0.74

 Mahat

-0.71

UCT

-0.71

POSITIVE LOGITS

ศึกษา

0.69

 Brod

0.66

 Wilk

0.66

 Hamm

0.65

ณา

0.65

 impostor

0.64

 Robb

0.64

 Holm

0.63

 Gorb

0.63

 Haye

0.62

Activations Density 1.806%

specific numerical values and their relationships within a structured context

Non-English or code-related text

response fausse

No Comments

No Known Activations