INDEX

Explanations

terms related to administrative processes and regulations

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

 jurors

-0.71

 suitors

-0.68

olella

-0.66

 JsonResult

-0.66

TacToe

-0.66

 Fores

-0.66

 Corbyn

-0.65

 Barca

-0.63

youtu

-0.63

Lup

-0.63

POSITIVE LOGITS

 administration

1.20

ModelAdmin

1.19

 administrations

1.13

 administrators

1.13

 Administration

1.10

 Administ

1.09

ADM

1.05

administ

1.03

administration

1.02

 administra

1.02

Activations Density 0.017%

terms related to administrative processes and regulations

No Comments

No Known Activations