INDEX

Explanations

references to experimental assays and diagnostic tests

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.1.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

 numberOfRows

-0.71

MLLoader

-0.62

QMetaType

-0.55

setContentView

-0.52

 CanadaChoose

-0.52

WriteTagHelper

-0.52

 UserManager

-0.51

mädchen

-0.51

 catho

-0.50

 Sanders

-0.48

POSITIVE LOGITS

EX

3.37

EX

3.20

Ex

3.18

Ex

3.15

ex

2.82

ex

2.14

exc

1.90

exp

1.82

EXC

1.80

EXC

1.78

Activations Density 0.129%

references to experimental assays and diagnostic tests

No Comments

No Known Activations