INDEX

Explanations

code-related terms, especially error messages and JavaScript elements

oai_token-act-pair · gemini-2.0-flash

keywords related to errors in JavaScript

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

programming code

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

Not in Any Lists

No Comments

Negative Logits

Efq

-0.84

 houſe

-0.79

 Houſe

-0.75

 Theſe

-0.73

ſelf

-0.73

 ویکی‌آمباردا

-0.72

 raiſ

-0.69

 ſeveral

-0.67

 themſelves

-0.67

 itſelf

-0.66

POSITIVE LOGITS

MessageTagHelper

0.56

fjspx

0.52

 true

0.51

true

0.49

^\

0.49

CrossRef

0.48

Ent

0.48

son

0.48

orianCalendar

0.47

ono

0.47

Activations Density 4.957%

code-related terms, especially error messages and JavaScript elements

keywords related to errors in JavaScript

programming code

No Comments

No Known Activations

code-related terms, especially error messages and JavaScript elements

keywords related to errors in JavaScript

programming code

No Comments

No Known Activations