INDEX

Explanations

references to specific locations and roles within a workplace setting

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

 unknownFields

-0.54

 cancellation

-0.53

gæ

-0.52

 bulunur

-0.52

 Became

-0.50

 emigration

-0.50

 varandra

-0.50

 sahiptir

-0.49

 ddelweddau

-0.49

 besök

-0.49

POSITIVE LOGITS

 doing

1.60

 trying

1.59

 looking

1.44

 attempting

1.42

 enjoying

1.37

 working

1.34

 performing

1.31

 making

1.27

 playing

1.23

 taking

1.20

Activations Density 0.569%

references to specific locations and roles within a workplace setting

No Comments

No Known Activations