INDEX

Explanations

occurrences of the pronoun "I" and related expressions of self-reference

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

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

iented

-0.73

CloseOperation

-0.70

 مشين

-0.69

WebServlet

-0.66

 Monfieur

-0.64

élev

-0.64

adaptiveStyles

-0.62

 SDLK

-0.61

 Theſe

-0.60

 againſt

-0.60

POSITIVE LOGITS

am

0.83

 když

0.59

Am

0.58

 guess

0.57

midler

0.54

AM

0.51

don

0.51

 anledning

0.50

 iVar

0.48

droje

0.47

Activations Density 0.196%

occurrences of the pronoun "I" and related expressions of self-reference

No Comments

No Known Activations