INDEX

Explanations

core project details and specifications related to design or construction.

oai_token-act-pair · gpt-4o-mini Triggered by @bot

content related to construction and design projects.

oai_token-act-pair · gpt-3.5-turbo Triggered by @bot

phrases or sentences describing design and development processes, especially related to product or website creation.

oai_token-act-pair · claude-3-5-sonnet-20240620 Triggered by @bot

Tokens followed by sentence-starting words

np_acts-logits-general · gemini-2.0-flash

originally. initially. first. begins

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

出版年

-0.87

testens

-0.79

 empires

-0.65

たまに

-0.65

flashdata

-0.64

 actionMode

-0.64

 fometimes

-0.63

AutoresizingMask

-0.63

你是不是

-0.62

 Shakspeare

-0.62

POSITIVE LOGITS

 originally

0.90

 original

0.84

 Originally

0.80

originally

0.79

 initially

0.78

 painstaking

0.78

 ursprünglich

0.75

Originally