INDEX

Explanations

irregularities or anomalies in narrative contexts

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

Code, references, or numbers in parentheses/brackets

np_acts-logits-general · gemini-2.0-flash

figure references

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.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

 pinulongan

-0.79

parsedMessage

-0.76

 Вікіпе

-0.66

 scattata

-0.62

 Beleuchtung

-0.61

JspWriter

-0.61

GTCX

-0.61

 pronti

-0.60

 kaarangay

-0.60

ρίου

-0.59

POSITIVE LOGITS

[toxicity=0]

1.03

 صوتيه

0.61

0.53

randomUUID

0.51

</h4>

0.50

Geografía

0.50

amente

0.48

DbHelper

0.48

 للمعارف

0.48

TRIBUN

0.47

Activations Density 0.024%

irregularities or anomalies in narrative contexts

Code, references, or numbers in parentheses/brackets

figure references

No Comments

No Known Activations