INDEX

Explanations

references to competency and capability in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

DockStyle

-0.81

 doInBackground

-0.79

 estekak

-0.77

 виправивши

-0.71

 المعيارى

-0.71

AndEndTag

-0.70

 pleaſure

-0.67

󠁢

-0.66

setupUi

-0.66

 hâte

-0.65

POSITIVE LOGITS

 competent

1.31

competent

1.01

 capable

0.94

 Compet

0.87

Compet

0.86

 competence

0.83

 competency

0.79

ef

0.77

 compet

0.76

compet

0.76

Activations Density 0.087%

references to competency and capability in various contexts

No Comments

No Known Activations