INDEX

Explanations

terms related to legal and regulatory language, especially those implying consequence or impact

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-65k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_65k/average_l0_72

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

65,536

Data Type

float32

Hook Name

blocks.12.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

-0.57

-0.54

-0.50

hip

-0.49

-0.48

ち

-0.48

-0.46

шаго

-0.45

POSITIVE LOGITS

Datuak

1.13

 autorytatywna

1.11

Tembelea

1.06

 AssemblyTitle

1.01

NUMX

0.94

IntoConstraints

0.93

+:+

0.91

tagHelperRunner

0.89

 AssemblyVersion

0.88

WriteTagHelper

0.88

Activations Density 0.174%

terms related to legal and regulatory language, especially those implying consequence or impact

No Comments

No Known Activations