INDEX

Explanations

elements related to legal and judicial processes, particularly focusing on waivers, admissions, and the voluntariness of statements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

 createState

-0.68

IUrlHelper

-0.62

 архивлан

-0.61

BASIC

-0.55

thunk

-0.54

remacy

-0.54

occupe

-0.53

Basic

-0.53

 cuda

-0.52

 surmounted

-0.52

POSITIVE LOGITS

 intentional

2.00

 deliberate

1.89

 intentionally

1.85

 deliberately

1.71

intention

1.65

 purposely

1.57

 Inten

1.54

 intention

1.54

 Intention

1.52

 consciously

1.52

Activations Density 0.565%

elements related to legal and judicial processes, particularly focusing on waivers, admissions, and the voluntariness of statements

No Comments

No Known Activations