INDEX

Explanations

terms related to tracks or tracking 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 @ 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

 Morley

-0.76

 Gerr

-0.71

المناصب

-0.71

 Maier

-0.70

 Valeria

-0.68

 coloriage

-0.68

 écl

-0.68

ngOnInit

-0.67

 newValue

-0.67

 Holman

-0.65

POSITIVE LOGITS

 tracks

2.37

 track

2.36

 Track

2.32

 TRACK

2.23

 Tracks

2.21

Track

2.19

track

2.15

tracks

2.08

TRACK

2.07

Tracks

1.91

Activations Density 0.037%

terms related to tracks or tracking in various contexts

No Comments

No Known Activations