INDEX

Explanations

terms related to trajectories or tracing paths

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

ValueStyle

-1.15

 Heilig

-0.85

 Keim

-0.85

Спољашње

-0.85

Annette

-0.84

ngOnInit

-0.81

 Eisenberg

-0.81

 vieilles

-0.80

 Anſ

-0.80

 LoggerFactory

-0.80

POSITIVE LOGITS

Tra

2.10

Tra

2.02

tra

2.01

tra

1.95

TRA

1.74

Trax

1.45

TRA

1.33

 Trapp

1.29

TR

1.26

 тра

1.21

Activations Density 0.110%

terms related to trajectories or tracing paths

No Comments

No Known Activations