INDEX

Explanations

references to configuration settings and file structures within a programming context

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

New Auto-Interp

Configuration

google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.20.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

<bos>

-0.52

(_.

-0.45

throw

-0.43

be

-0.43

LastName

-0.43

they

-0.43

YYYY

-0.42

–

-0.42

to

-0.41

will

-0.41

POSITIVE LOGITS

 config

1.21

 Config

1.19

Config

1.14

config

1.08

 getConfig

1.00

 CONFIG

1.00

getConfig

0.98

setConfig

0.95

 configs

0.88

CONFIG

0.88

Activations Density 0.022%

references to configuration settings and file structures within a programming context

No Comments

No Known Activations