INDEX

Explanations

concepts related to governance and public policy

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Neighbors

-1.09

 favors

-1.09

 confiable

-1.07

neighbors

-1.05

 neighbors

-1.05

 Neighbors

-1.02

FAVOR

-1.01

 harbors

-1.01

Favor

-1.00

 favorable

-0.99

POSITIVE LOGITS

Whilst

1.84

 Whilst

1.73

initialise

1.56

 whilst

1.53

COLOUR

1.44

 specialises

1.44

centre

1.42

 realises

1.41

 realise

1.41

Colour

1.41

Activations Density 2.858%

concepts related to governance and public policy

No Comments

No Known Activations

concepts related to governance and public policy

No Comments

No Known Activations