INDEX

Explanations

function declarations and their return types in code

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

BagConstraints

-0.58

 esternos

-0.57

 MainAxisSize

-0.54

Tikang

-0.51

Ӏ

-0.50

Citiți

-0.50

lankton

-0.49

 colspan

-0.49

 regularity

-0.49

raim

-0.49

POSITIVE LOGITS

 return

0.92

return

0.90

 Return

0.70

 RETURN

0.67

 returns

0.64

 returned

0.64

 Returns

0.61

Return

0.59

 RETURNS

0.58

 retorna

0.58

Activations Density 0.051%

function declarations and their return types in code

No Comments

No Known Activations