INDEX

Explanations

scientific terms and processes related to biological analysis

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.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

 Afterward

-0.97

けっこう

-0.87

 marvelous

-0.79

 grayish

-0.75

Proper

-0.75

Kinds

-0.72

canceled

-0.71

Neighbors

-0.70

favorite

-0.70

 stället

-0.69

POSITIVE LOGITS

Whilst

1.92

 Whilst

1.85

 whilst

1.58

 utilising

1.39

 optimisation

1.36

 utilised

1.31

 optimised

1.30

 utilise

1.28

 localised

1.27

 optimise

1.23

Activations Density 1.722%

scientific terms and processes related to biological analysis

No Comments

No Known Activations