INDEX

Explanations

terms related to assistance and support

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Sten

-0.77

æ

-0.77

يبة

-0.74

 Wally

-0.74

styleType

-0.74

PreferredItem

-0.73

anair

-0.72

 ApiException

-0.71

tvrt

-0.71

mã

-0.70

POSITIVE LOGITS

 help

1.53

 HELP

1.42

help

1.39

HELP

1.37

 Help

1.32

Help

1.25

 helps

1.23

 helping

1.21

Helping

1.17

Helps

1.15

Activations Density 0.081%

terms related to assistance and support

No Comments

No Known Activations