INDEX

Explanations

words related to "ins" and its various forms, indicating processes or states involving inclusivity or involvement

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

 EconPapers

-0.80

 Skeletal

-0.76

zegor

-0.75

={({

-0.74

 Vara

-0.73

 Thayer

-0.73

atern

-0.72

pâ

-0.72

 Zagreb

-0.71

 Projector

-0.69

POSITIVE LOGITS

Ins

2.29

Ins

2.17

ins

1.91

INS

1.77

ins

1.75

 insulation

1.48

INS

1.44

 Insulation

1.41

 insulators

1.27

 insu

1.25

Activations Density 0.064%

words related to "ins" and its various forms, indicating processes or states involving inclusivity or involvement

No Comments

No Known Activations