INDEX

Explanations

classifications and categories within structured systems

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 19-gemmascope-mlp-16k

Configuration

google/gemma-scope-2b-pt-mlp/layer_19/width_16k/average_l0_109

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.19.hook_mlp_out

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

-0.50

-0.48

“

-0.46

com

-0.45

big

-0.45

-0.44

bg

-0.43

-0.42

-0.41

POSITIVE LOGITS

 houſe

1.16

 itſelf

1.13

 purpoſe

1.12

 myſelf

1.12

ſelf

1.09

 poffible

1.02

 whoſe

1.01

 Monfieur

1.01

 iſt

1.01

 pleaſure

1.00

Activations Density 0.533%

classifications and categories within structured systems

No Comments

No Known Activations