INDEX

Explanations

coding-related terms and functions

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

get, is, has

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 16-gemmascope-res-65k

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_65k/average_l0_128

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

65,536

Data Type

float32

Hook Name

blocks.16.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

 also

-0.58

-0.56

in

-0.54

as

-0.54

-0.52

 just

-0.51

 perhaps

-0.51

POSITIVE LOGITS

 purpoſe

1.47

 myſelf

1.33

 pleaſure

1.33

 leaſt

1.29

 Monfieur

1.27

 Anſ

1.24

 Theſe

1.23

 ſtate

1.23

 fubject

1.23

ſelf

1.23

Activations Density 0.133%

coding-related terms and functions

get, is, has

No Comments

No Known Activations