INDEX

Explanations

references to teaching and training activities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.23.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

endphp

-0.61

zeiti

-0.55

iedy

-0.55

 practicing

-0.53

-0.52

 practising

-0.51

Roster

-0.51

 Examiners

-0.50

 Roster

-0.46

 emend

-0.46

POSITIVE LOGITS

 courses

1.38

 course

1.24

 classes

1.22

 workshops

1.22

 workshop

1.10

courses

1.04

classes

0.99

 Courses

0.99

course

0.97

 curso

0.91

Activations Density 0.211%

references to teaching and training activities

No Comments

No Known Activations