INDEX

Explanations

code syntax and related terms

oai_token-act-pair · gemini-2.0-flash

code snippets

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.7.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

 propOrder

-0.57

期刊论文

-0.48

Portail

-0.45

 صوتيه

-0.42

<bos>

-0.42

 CreateTagHelper

-0.41

راحل

-0.41

*@

-0.41

)<

-0.40

"]

-0.40

POSITIVE LOGITS

RenderAtEndOf

0.83

 Gallimard

0.68

\{\\

0.66

NameInMap

0.66

发表于

0.65

ఔ

0.63

sidemargin

0.63

 appartiennent

0.60

省市镇

0.60

UserScript

0.59

Activations Density 1.078%

code syntax and related terms

code snippets

No Comments

No Known Activations