INDEX

Explanations

terms related to removal or exclusion

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.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

 StatefulWidget

-0.60

 podjela

-0.45

textInput

-0.44

Addo

-0.44

 grills

-0.43

stdint

-0.42

 promise

-0.42

గా

-0.41

 BoxFit

-0.41

Mixtures

-0.41

POSITIVE LOGITS

 removal

1.37

 remove

1.35

 Removal

1.33

 removing

1.32

 removed

1.30

 Removing

1.30

 removes

1.28

 Remove

1.26

 Removed

1.23

 removals

1.23

Activations Density 0.546%

terms related to removal or exclusion

No Comments

No Known Activations