INDEX

Explanations

programming annotations or metadata in the document

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.4.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

FailureListener

-0.94

 linkovi

-0.85

IVEREF

-0.79

AddTagHelper

-0.79

bootstrapcdn

-0.79

PerformLayout

-0.78

Personendaten

-0.78

WriteTagHelper

-0.77

 AssemblyVersion

-0.76

invokeLater

-0.73

POSITIVE LOGITS

 rowspan

0.56

hobia

0.54

*@

0.53

#![

0.53

 Sien

0.51

quoise

0.51

}")]

0.49

ंदीखरीदारी

0.48

 Saif

0.48

 http

0.47

Activations Density 0.107%

programming annotations or metadata in the document

No Comments

No Known Activations