INDEX

Explanations

technical terms related to programming and data handling

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

Efq

-1.18

 uſed

-1.10

 Theſe

-1.06

 myſelf

-1.04

 itſelf

-1.00

 Majefty

-0.98

 ―――――

-0.97

 pleaſure

-0.95

 ſhould

-0.94

 Monfieur

-0.94

POSITIVE LOGITS

:✨

0.73

 Cordero

0.67

CppMethod

0.65

idigung

0.64

ambiguation

0.61

原始内容存档于

0.60

 Elli

0.59

productList

0.56

CLAIMER

0.56

Activations Density 0.127%

technical terms related to programming and data handling

No Comments

No Known Activations