INDEX

Explanations

technical terms and data structures related to programming and data processing

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

<eos>

-0.71

).

-0.67

all

-0.65

-0.64

↵↵

-0.63

-0.59

↵

-0.58

...

-0.57

".

-0.56

POSITIVE LOGITS

AccessorTable

1.33

MemoryWarning

1.12

tagHelperRunner

1.12

Geplaatst

1.10

下载附件

1.09

bootstrapcdn

1.09

 protoimpl

1.06

WebVitals

1.05

MLLoader

1.00

IsMutable

0.99

Activations Density 0.686%

technical terms and data structures related to programming and data processing

No Comments

No Known Activations