INDEX

Explanations

terms related to optional and mandatory features in a technical context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.31.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

 للاسماء

-0.72

awtextra

-0.60

 onCreateView

-0.60

httphttps

-0.57

 AssemblyCulture

-0.56

 للمعارف

-0.55

WireFormatLite

-0.54

dafx

-0.54

contentLoaded

-0.54

Personendaten

-0.53

POSITIVE LOGITS

 optional

2.92

optional

2.56

 Optional

2.50

Optional

2.48

 OPTIONAL

2.20

OPTIONAL

2.06

 optionally

2.02

 voluntary

1.94

 opcional

1.87

opcional

1.78

Activations Density 0.560%

terms related to optional and mandatory features in a technical context

No Comments

No Known Activations