INDEX

Explanations

words and phrases related to business, certification, and organizations

oai_token-act-pair · gemini-2.0-flash

programming-related terms or syntactical elements

np_token-act-pair-logits · gpt-4o-mini

pointers

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.ln2.hook_normalized

Architecture

jumprelu_transcoder

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Negative Logits

 виправивши

-0.59

RenderAtEndOf

-0.58

sizeCache

-0.56

ipients

-0.56

UnusedPrivate

-0.55

glGen

-0.53

 ſeveral

-0.53

Ẽ

-0.52

teger

-0.52

mişti

-0.52

POSITIVE LOGITS

__':

0.59

 kasarigan

0.56

 AspNetCore

0.54

specialchars

0.50

 AppCompat

0.48

 ✭✭

0.47

yntaxException

0.47

 IFTT

0.47

__":

0.46

__":

0.46

Activations Density 8.895%

words and phrases related to business, certification, and organizations

programming-related terms or syntactical elements

pointers

No Known Activations