INDEX

Explanations

references to scientific journals and publications

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

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

Efq

-0.98

 ProtoMessage

-0.94

 itſelf

-0.91

 Monfieur

-0.91

 ſeveral

-0.90

 myſelf

-0.89

 raiſ

-0.88

 reaſon

-0.88

 ſever

-0.87

 fubject

-0.84

POSITIVE LOGITS

PhysRevD

1.42

PhysRevLett

0.79

PhysRev

0.60

0.54

0.51

en

0.49

openzeppelin

0.47

AutoField

0.47

en

0.46

stateParams

0.45

Activations Density 0.239%

references to scientific journals and publications

No Comments

No Known Activations