INDEX

Explanations

terms related to encoding and decoding processes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

 Stoner

-0.91

AsUp

-0.80

:+:

-0.74

viewpager

-0.73

ergies

-0.66

पया

-0.64

locationManager

-0.63

\,,

-0.63

 mView

-0.63

Życiorys

-0.62

POSITIVE LOGITS

 encode

1.58

 Encode

1.55

encode

1.53

 Decode

1.48

 encodes

1.45

Decode

1.42

Encode

1.42

 encoded

1.39

 encoding

1.37

 decode

1.32

Activations Density 0.100%

terms related to encoding and decoding processes

No Comments

No Known Activations