INDEX

Explanations

mathematical symbols and expressions, particularly those involving matrices and linear algebra

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

...

-0.69

↵

-0.67

↵↵

-0.64

-0.61

...

-0.60

…

-0.59

....

-0.52

шан

-0.52

…

-0.50

......

-0.49

POSITIVE LOGITS

 ExecuteAsync

0.93

 CreateTagHelper

0.88

Efq

0.87

tagHelperRunner

0.85



0.84

WireFormatLite

0.82

 cherchés

0.81

 Monfieur

0.79

RegistryLite

0.78

 Theſe

0.78

Activations Density 0.585%

mathematical symbols and expressions, particularly those involving matrices and linear algebra

No Comments

No Known Activations