INDEX

Explanations

scientific terms related to experimental design and methodology

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.10.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

Whilst

-1.09

 Whilst

-1.09

 whilst

-0.94

-0.85

 Amongst

-0.85

…..

-0.80

の為

-0.80

 diatas

-0.80

 amongst

-0.79

 didalam

-0.78

POSITIVE LOGITS

 itſelf

1.00

GEBURTSDATUM

1.00

Vidite

0.98

—

0.98

—

0.94

 fubject

0.93

 myſelf

0.91

WriteBarrier

0.90

].)

0.87

 Audiodateien

0.87

Activations Density 1.770%

scientific terms related to experimental design and methodology

No Comments

No Known Activations