INDEX

Explanations

terminology related to railway locomotives and their operational details

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

 nakalista

-0.72

ArrowToggle

-0.60

Życiorys

-0.59

ciutto

-0.58

alanta

-0.55

Билгалдахарш

-0.55

 Nebula

-0.53

 ModelExpression

-0.52

lugin

-0.52

 Landfill

-0.52

POSITIVE LOGITS

 train

1.61

 rail

1.54

 trains

1.45

 railway

1.44

 Train

1.39

 Rail

1.38

 railroad

1.35

 rails

1.33

Train

1.31

Rail

1.31

Activations Density 0.241%

terminology related to railway locomotives and their operational details

No Comments

No Known Activations