INDEX

Explanations

references to specific variables or identifiers in a programming or mathematical context

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

Token "Y" followed by numbers

np_acts-logits-general · gemini-2.0-flash

Y identifiers

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Personensuche

-0.83

httphttps

-0.82

uxxxx

-0.81

 المعيارى

-0.72

UIControlState

-0.69

verwijspagina

-0.68

 typelib

-0.68

#+#

-0.62

:].

-0.61

RTEE

-0.61

POSITIVE LOGITS

Yel

1.03

Yol

0.97

 getY

0.96

Yag

0.94

Yat

0.90

 Yates

0.89

Yemen

0.89

 Yvette

0.88

 Yorke

0.87

Yar

0.86

Activations Density 0.226%

references to specific variables or identifiers in a programming or mathematical context

Token "Y" followed by numbers

Y identifiers

No Comments

No Known Activations