INDEX

Explanations

code snippets involving the NumPy library for array manipulation

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ExtendWith

-0.83

EnableWeb

-0.75

]")]

-0.73

Хьажоргаш

-0.68

TestingModule

-0.68

 himo

-0.67

 linden

-0.63

}")]

-0.62

 Dresden

-0.62

 Dinah

-0.62

POSITIVE LOGITS

np

1.13

 numpy

0.95

np

0.88

asarray

0.82

npy

0.81

umpy

0.69

 spare

0.69

toMatch

0.68

numpy

0.68

EXPR

0.66

Activations Density 0.036%

code snippets involving the NumPy library for array manipulation

No Comments

No Known Activations