INDEX

Explanations

references and annotations within a document

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

+#+#

-0.89

 ModelExpression

-0.87

SpringBootTest

-0.86

 незавершена

-0.83

sidemargin

-0.80

ruptedException

-0.79

 Theſe

-0.77

]--;

-0.76

tvguidetime

-0.75

CompleteListener

-0.74

POSITIVE LOGITS

at

1.80

At

1.03

At

1.01

at

0.95

AtEndOf

0.75

ở

0.69

 конце

0.65

ท้าย

0.63

 tại

0.63

 vorne

0.61

Activations Density 0.311%

references and annotations within a document

No Comments

No Known Activations