INDEX

Explanations

references to data handling and distribution processes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

findpost

-1.02

 Normdatei

-0.85

oa̍t

-0.76

AccessorTable

-0.74

IVEREF

-0.72

UnusedPrivate

-0.72

LookAnd

-0.71

TagMode

-0.70

transQ

-0.68

 MenuView

-0.67

POSITIVE LOGITS

 along

1.17

along

1.00

 juntamente

0.99

 alongside

0.99

 wraz

0.89

 ALONG

0.86

 junto

0.82

 Along

0.81

Along

0.79

 ready

0.78

Activations Density 0.766%

references to data handling and distribution processes

No Comments

No Known Activations