INDEX

Explanations

changes

np_token-act-pair-logits · gemini-2.0-flash

name of places and the word change and it's derivatives

oai_token-act-pair · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_16/width_16k/average_l0_10

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.ln2.hook_normalized

Architecture

jumprelu_transcoder

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

HtmlAttribute

-0.68

 exception

-0.59

 myſelf

-0.57

onAttach

-0.54

 wireType

-0.54

agot

-0.51

ToAction

-0.50

 himſelf

-0.50

Getenv

-0.49

 Shakspeare

-0.49

POSITIVE LOGITS

 '\\;'

0.66

fromnode

0.56

ImageField

0.56

 tartalomajánló

0.55

AddTagHelper

0.54

;}

0.50

 validamos

0.48

 bedenken

0.48

 estri

0.48

 Архивировано

0.48

Activations Density 0.301%

changes

name of places and the word change and it's derivatives

No Comments

No Known Activations