INDEX

Explanations

terms related to film and production

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

SBATCH

-1.00

Efq

-0.95

fjspx

-0.92

tonsoft

-0.88

 AttributeSet

-0.86

 CiNii

-0.85

mybatisplus

-0.84

 cdti

-0.84

хьтан

-0.83

 Houſe

-0.82

POSITIVE LOGITS

 production

3.20

 producing

3.10

 produce

2.89

 produced

2.89

 Production

2.86

production

2.80

 Producing

2.78

Production

2.76

producing

2.75

produce

2.72

Activations Density 0.106%

terms related to film and production

No Comments

No Known Activations