INDEX

Explanations

code related to web applications, especially involving the term "Web"

oai_token-act-pair · gemini-2.0-flash

programming code/web development

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.23.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

KURZBESCHREIBUNG

-1.00

 rospy

-0.71

LookAnd

-0.71

 виправивши

-0.69

GEBURTSDATUM

-0.67

SuppressMessage

-0.66

bitField

-0.66

<bos>

-0.65

Personendaten

-0.64

ousands

-0.63

POSITIVE LOGITS

filter

0.58

el

0.57

 bogotá

0.52

fb

0.51

zo

0.51

ele

0.51

 démocr

0.51

 eccl

0.50

inst

0.49

le

0.49

Activations Density 0.335%

code related to web applications, especially involving the term "Web"

programming code/web development

No Comments

No Known Activations