INDEX

Explanations

variables and their associated sizes in programming code

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

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_1m/average_l0_107

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

1,048,576

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

principalTable

-0.57

posedge

-0.51

 GenerationType

-0.50

Opponent

-0.48

 Maggio

-0.47

ographiques

-0.47

日発売

-0.46

Дереккөздер

-0.46

 ویکی‌پدیا

-0.45

POSITIVE LOGITS

[_

0.61

}-${

0.56

ństwa

0.55

}/${

0.54

énéral

0.53

[-

0.53

[_

0.52

Ƚ

0.52

érience

0.52

$[-

0.52

Activations Density 0.006%

variables and their associated sizes in programming code

No Comments

No Known Activations