INDEX

Explanations

statistical results including test statistics, p-values, and confidence intervals

oai_token-act-pair · gemini-2.0-flash

statistical significance markers

np_token-act-pair-logits · gpt-4o-mini

statistical significance in papers

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.ln2.hook_normalized

Architecture

jumprelu_transcoder

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 ExecuteAsync

-0.90

__':

-0.83

__":

-0.82

 nakalista

-0.82

__":

-0.81

__':

-0.80

featureID

-0.77

SharedDtor

-0.76

DataAnnotations

-0.75

__);

-0.75

POSITIVE LOGITS

 Dawkins

0.42

Pwd

0.42

multirow

0.42

lig

0.40

nth

0.40

 Hauses

0.39

 Doppel

0.38

ELA

0.37

LastName

0.37

rs

0.37

Activations Density 3.164%

statistical results including test statistics, p-values, and confidence intervals

statistical significance markers

statistical significance in papers

No Comments

No Known Activations