INDEX

Explanations

technical terms and constructs related to programming and data types

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

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_32k/average_l0_76

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

32,768

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

há

-0.52

Bou

-0.50

 enjoyed

-0.46

bad

-0.46

 code

-0.45

jen

-0.44

 just

-0.44

didReceive

-0.44

ente

-0.43

POSITIVE LOGITS

 typelib

0.99

 autorytatywna

0.95

 שוליים

0.82



0.78

RectangleBorder

0.78

 ddelweddau

0.75

Rohy

0.74

ViewFeatures

0.73

InSection

0.72

SourceChecksum

0.72

Activations Density 0.202%

technical terms and constructs related to programming and data types

No Comments

No Known Activations