INDEX

Explanations

patterns of formatted text or repeated sequences

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.19.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

********/

-0.73

Portail

-0.70

*********/

-0.65

prefixer

-0.64

Hauptartikel

-0.63

 Perrin

-0.61

 esternos

-0.61

IGraphics

-0.61

**********/

-0.59

ProgressHUD

-0.59

POSITIVE LOGITS

================

1.33

============

0.74

==============

0.72

=========

0.70

=======

0.69

===========

0.68

===============

0.68

 ====

0.66

====

0.65

=============

0.64

Activations Density 0.072%

patterns of formatted text or repeated sequences

No Comments

No Known Activations