INDEX

Explanations

terms related to enabling and disabling features or settings

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

 كومونز

-0.96

bcrypt

-0.77

 CreateTagHelper

-0.75

 votos

-0.74

 fjor

-0.72

StateException

-0.72

gdx

-0.70

тру

-0.69

TRS

-0.69

 Wissens

-0.68

POSITIVE LOGITS

 ENABLE

1.30

 Enable

1.28

Ena

1.28

 enable

1.23

 Enables

1.23

 OnEnable

1.23

enabled

1.20

 enables

1.18

 enabled

1.17

 Enabled

1.15

Activations Density 0.113%

terms related to enabling and disabling features or settings

No Comments

No Known Activations